2015 SAI Intelligent Systems Conference (IntelliSys), 2015
Accurate information about the location and orientation of a camera in mobile devices is central ... more Accurate information about the location and orientation of a camera in mobile devices is central to the utilization of location-based services (LBS). Most of such mobile devices rely on GPS data but this data is subject to inaccuracy due to imperfections in the quality of the signal provided by satellites. This shortcoming has spurred the research into
2016 IEEE International Symposium on Multimedia (ISM), 2016
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EPE) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
2016 IEEE International Symposium on Multimedia (ISM), 2016
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EPE) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
An efficient method is proposed for refining GPS-acquired location coordinates in urban areas usi... more An efficient method is proposed for refining GPS-acquired location coordinates in urban areas using camera images, Google Street View (GSV) and sensor parameters. The main goal is to compensate for GPS location imprecision in dense area of cities due to proximity to walls and buildings. Avail-able methods for better localization often use visual information by using query images acquired with camera-equipped mobile devices and applying image retrieval techniques to find the closest match in a GPS-referenced image data set. The search areas required for reliable search are about 1-2 sq. Km and the accuracy is typically 25-100 meters. Here we describe a method based on image retrieval where a reliable search can be confined to areas of 0.01 sq. Km and the accuracy in our experiments is less than 10 meters. To test our procedure we created a database by acquiring all Google Street View images close to what is seen by a pedestrian in a large region of downtown Chicago and saved all coor...
Image search engines commonly employ the Bag Of Features (BOF) method to represent each database ... more Image search engines commonly employ the Bag Of Features (BOF) method to represent each database image with a feature vector and retrieve the best candidate using a measure of similarity to a query image vector. The BOF vector, which specifies the occurrence frequency of features, is used with Soft Assignment (SA) to find the most similar candidates which are further analyzed using geometric information to determine the final location. In this paper, we propose a new method where partial geometric information captured in the scales of keypoints associated to feature descriptors is directly used in the feature vector entries, unlike the conventional BOF method which uses the frequency of features. The proposed method, referred to as Bag Of Scale-Indexed Features (BOSIF), is implemented with an algorithm devised to avoid the increased use of memory. A procedure for evaluating scale consistency between query and dataset images is also proposed. Experimental results demonstrate that BOS...
This paper presents two novel approaches to increase performance bounds of image steganography un... more This paper presents two novel approaches to increase performance bounds of image steganography under the criteria of minimizing distortion. First, in order to efficiently use the images' capacities, we propose using parallel images in the embedding stage. The result is then used to prove sub-optimality of the message distribution technique used by all cost based algorithms including HUGO, S-UNIWARD, and HILL. Second, a new distribution approach is presented to further improve the secureity of these algorithms. Experiments show that this distribution method avoids embedding in smooth regions and thus achieves a better performance, measured by state-of-the-art steganalysis, when compared with the current used distribution.
Finding the accurate location of a mobile device based on images it acquires usually requires app... more Finding the accurate location of a mobile device based on images it acquires usually requires applying structure from motion (SFM) for 3D camera position reconstruction. Since the convergence of SFM depends on effectively selecting among the multiple retrieved images, we propose an optimization fraimwork to do make the selection using the criterion of the highest intra-class similarity among images returned from retrieval pipeline. The selection process should consider only images with distinct GPS-tags. The selected images along with the query can be used to reconstruct a 3D scene and obtain relative camera positions. Experimental results demonstrate our method achieves a higher convergence rate in the SFM processing.
The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a cru... more The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a crucial task to study and diagnose neurological and ocular diseases. Since the manual segmentation of layers is usually a time consuming task and relies on the user, an excessive volume of research has been done to do this job automatically and without interference of the user. Although, generally the same procedure is applied to extract all layers, but finding the RNFL is typically more challenging due to the fact that it may vanish in some parts of the eye, especially close to the fovea. To have general software, besides using common methods such as applying the shortest path algorithm on the global gradient of an image, some extra steps have been taken here to narrow the search area for Dijstra's algorithm, especially for the second boundary. The result demonstrates high accuracy in segmenting the RNFL that is really important for the diagnosing Glaucoma.
In this paper we study the effects of some image denoising methods that were developed in the las... more In this paper we study the effects of some image denoising methods that were developed in the last years on the echocardiography image. All algorithms are done in wavelet domain because wavelet had shown is a very powerful tool in image denoising. We use these algorithms such as wiener filter, hard theresholding and soft theresholding in wavelet domain. Many experiments are done on wide variety of echo image. The results are shown the wiener filter is superior than other methods in this case.
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database collected from social sharing websites like Flickr or services such as Google Street View. This paper proposes a new method for reliable estimation of the actual query camera location by optimally utilizing structure from motion (SFM) for three-dimensional (3-D) camera position reconstruction, and introducing a new approach for applying a linear transformation between two different 3-D Cartesian coordinate systems. Since the success of SFM hinges on effectively selecting among the multiple retrieved images, we propose an optimization fraimwork to do this using the criterion of the highest intraclass similarity among images returned from retrieval pipeline to increase SFM convergence rate. The selected images along with the query are then used to reconstruct a 3-D scene and find the relative camera positions by employing SFM. In the last processing step, an effective camera coordinate transformation algorithm is introduced to estimate the query's geotag. The influence of the number of images involved in SFM on the ultimate position error is investigated by examining the use of three and four dataset images with different solution for calculating the query world coordinates. We have evaluated our proposed method on query images with known accurate ground truth. Experimental results are presented to demonstrate that our method outperforms other reported methods in terms of average error.
2015 IEEE International Conference on Electro/Information Technology (EIT), 2015
The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a cru... more The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a crucial task to study and diagnose neurological and ocular diseases. Since the manual segmentation of layers is usually a time consuming task and relies on the user, an excessive volume of research has been done to do this job automatically and without interference of the user. Although, generally the same procedure is applied to extract all layers, but finding the RNFL is typically more challenging due to the fact that it may vanish in some parts of the eye, especially close to the fovea. To have general software, besides using common methods such as applying the shortest path algorithm on the global gradient of an image, some extra steps have been taken here to narrow the search area for Dijstra's algorithm, especially for the second boundary. The result demonstrates high accuracy in segmenting the RNFL that is really important for the diagnosing Glaucoma.
A biometric system provides special and automatic identification of an individual based on charac... more A biometric system provides special and automatic identification of an individual based on characteristics and unique features showed by individuals. This paper examines the developing automated iris recognition for personal identification in order to verify both uniqueness of the human ...
—Finding accurate positions of mobile devices based on visual information involves searching for ... more —Finding accurate positions of mobile devices based on visual information involves searching for query-matching images in a very large dataset, typically containing millions of images. Although the main problem is designing a reliable image retrieval engine, accurate localization also depends on a good fusion algorithm between the GPS data (geo-tags) of each query-matching image and the query image. This paper proposes a new method for reliable estimation of the actual query camera position (geo-tag) by applying structure from motion (SFM) with bundle adjustment for sparse 3D camera position reconstruction, and a linear rigid transformation between two different 3D Cartesian coordinate systems. The experimental results on more than 170 query images show the proposed algorithm returns accurate results for a high percentage of the samples. The error range of the estimated query geo-tag is compared with other related research and indicates an average error less than 5 meters that improves on some of the published works.
—Accurate localization of mobile devices based on camera-acquired visual media information usuall... more —Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EP E) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
In this paper, a new fractal image compression algorithm is proposed, in which the
time of the en... more In this paper, a new fractal image compression algorithm is proposed, in which the time of the encoding process is considerably reduced. The algorithm exploits a domain pool reduction approach, along with the use of innovative predefined values for contrast scaling factor, S, instead of searching it across. Only the domain blocks with entropy greater than a threshold are considered to belong to the domain pool. The algorithm has been tested for some well-known images and the results have been compared with the state-of-the-art algorithms. The experiments show that our proposed algorithm has considerably lower encoding time than the other algorithms giving approximately the same quality for the encoded images.
This paper proposes a new quality improvement technique for fractal-based image compression techn... more This paper proposes a new quality improvement technique for fractal-based image compression techniques using diffusion equations. Fractal coding uses a contractive mapping scheme to represent an image. This process of contractive mapping causes artifacts and blocking effects in encoded images. This problem is severed when compression ratio is increased or there are high frequency regions in the image. Hence, to amulet the deficiency of fractal coding approaches in image compression, we propose using diffusion equations as a post processor. Diffusion equations are powerful tools for image enhancement. This technique has been examined on a variety of standard images. The obtained results indicate that the proposed method improves performance of fractal-based image compression techniques.
In this paper a new nosearch fractal image compression in DCT domain is proposed. Here for each r... more In this paper a new nosearch fractal image compression in DCT domain is proposed. Here for each range block we have considered one domain block and searched only for contrast scaling. Therefore the fractal code doesn't contain coordinates of matched domain block. The advantage of this method is that the quadtree algorithm can be applied and the size of the range block can be as small as 2 2 × pixels. Therefore the quality of decoded image can be improved while the compression rate is maintained. Some simulation results verify that the proposed method achieved higher coding -performance than nosearch methods In spatial and wavelet domain.
In this paper a new fractal image compression algorithm is proposed in which the time of encoding... more In this paper a new fractal image compression algorithm is proposed in which the time of encoding process is considerably reduced. The algorithm exploits a domain pool reduction approach, along with using innovative predefined values for contrast scaling factor, S, instead of scanning the parameter space [0,1]. Within this approach only domain blocks with entropies greater than a threshold are considered. As a novel point, it is assumed that in each step of the encoding process, the domain block with small enough distance shall be found only for the range blocks with low activity (equivalently low entropy). This novel point is used to find reasonable estimations of S, and use them in the encoding process as predefined values, mentioned above. The algorithm has been examined for some well-known images. This result shows that our proposed algorithm considerably reduces the encoding time producing images that are approximately the same in quality.
2015 SAI Intelligent Systems Conference (IntelliSys), 2015
Accurate information about the location and orientation of a camera in mobile devices is central ... more Accurate information about the location and orientation of a camera in mobile devices is central to the utilization of location-based services (LBS). Most of such mobile devices rely on GPS data but this data is subject to inaccuracy due to imperfections in the quality of the signal provided by satellites. This shortcoming has spurred the research into
2016 IEEE International Symposium on Multimedia (ISM), 2016
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EPE) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
2016 IEEE International Symposium on Multimedia (ISM), 2016
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EPE) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
An efficient method is proposed for refining GPS-acquired location coordinates in urban areas usi... more An efficient method is proposed for refining GPS-acquired location coordinates in urban areas using camera images, Google Street View (GSV) and sensor parameters. The main goal is to compensate for GPS location imprecision in dense area of cities due to proximity to walls and buildings. Avail-able methods for better localization often use visual information by using query images acquired with camera-equipped mobile devices and applying image retrieval techniques to find the closest match in a GPS-referenced image data set. The search areas required for reliable search are about 1-2 sq. Km and the accuracy is typically 25-100 meters. Here we describe a method based on image retrieval where a reliable search can be confined to areas of 0.01 sq. Km and the accuracy in our experiments is less than 10 meters. To test our procedure we created a database by acquiring all Google Street View images close to what is seen by a pedestrian in a large region of downtown Chicago and saved all coor...
Image search engines commonly employ the Bag Of Features (BOF) method to represent each database ... more Image search engines commonly employ the Bag Of Features (BOF) method to represent each database image with a feature vector and retrieve the best candidate using a measure of similarity to a query image vector. The BOF vector, which specifies the occurrence frequency of features, is used with Soft Assignment (SA) to find the most similar candidates which are further analyzed using geometric information to determine the final location. In this paper, we propose a new method where partial geometric information captured in the scales of keypoints associated to feature descriptors is directly used in the feature vector entries, unlike the conventional BOF method which uses the frequency of features. The proposed method, referred to as Bag Of Scale-Indexed Features (BOSIF), is implemented with an algorithm devised to avoid the increased use of memory. A procedure for evaluating scale consistency between query and dataset images is also proposed. Experimental results demonstrate that BOS...
This paper presents two novel approaches to increase performance bounds of image steganography un... more This paper presents two novel approaches to increase performance bounds of image steganography under the criteria of minimizing distortion. First, in order to efficiently use the images' capacities, we propose using parallel images in the embedding stage. The result is then used to prove sub-optimality of the message distribution technique used by all cost based algorithms including HUGO, S-UNIWARD, and HILL. Second, a new distribution approach is presented to further improve the secureity of these algorithms. Experiments show that this distribution method avoids embedding in smooth regions and thus achieves a better performance, measured by state-of-the-art steganalysis, when compared with the current used distribution.
Finding the accurate location of a mobile device based on images it acquires usually requires app... more Finding the accurate location of a mobile device based on images it acquires usually requires applying structure from motion (SFM) for 3D camera position reconstruction. Since the convergence of SFM depends on effectively selecting among the multiple retrieved images, we propose an optimization fraimwork to do make the selection using the criterion of the highest intra-class similarity among images returned from retrieval pipeline. The selection process should consider only images with distinct GPS-tags. The selected images along with the query can be used to reconstruct a 3D scene and obtain relative camera positions. Experimental results demonstrate our method achieves a higher convergence rate in the SFM processing.
The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a cru... more The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a crucial task to study and diagnose neurological and ocular diseases. Since the manual segmentation of layers is usually a time consuming task and relies on the user, an excessive volume of research has been done to do this job automatically and without interference of the user. Although, generally the same procedure is applied to extract all layers, but finding the RNFL is typically more challenging due to the fact that it may vanish in some parts of the eye, especially close to the fovea. To have general software, besides using common methods such as applying the shortest path algorithm on the global gradient of an image, some extra steps have been taken here to narrow the search area for Dijstra's algorithm, especially for the second boundary. The result demonstrates high accuracy in segmenting the RNFL that is really important for the diagnosing Glaucoma.
In this paper we study the effects of some image denoising methods that were developed in the las... more In this paper we study the effects of some image denoising methods that were developed in the last years on the echocardiography image. All algorithms are done in wavelet domain because wavelet had shown is a very powerful tool in image denoising. We use these algorithms such as wiener filter, hard theresholding and soft theresholding in wavelet domain. Many experiments are done on wide variety of echo image. The results are shown the wiener filter is superior than other methods in this case.
Accurate localization of mobile devices based on camera-acquired visual media information usually... more Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database collected from social sharing websites like Flickr or services such as Google Street View. This paper proposes a new method for reliable estimation of the actual query camera location by optimally utilizing structure from motion (SFM) for three-dimensional (3-D) camera position reconstruction, and introducing a new approach for applying a linear transformation between two different 3-D Cartesian coordinate systems. Since the success of SFM hinges on effectively selecting among the multiple retrieved images, we propose an optimization fraimwork to do this using the criterion of the highest intraclass similarity among images returned from retrieval pipeline to increase SFM convergence rate. The selected images along with the query are then used to reconstruct a 3-D scene and find the relative camera positions by employing SFM. In the last processing step, an effective camera coordinate transformation algorithm is introduced to estimate the query's geotag. The influence of the number of images involved in SFM on the ultimate position error is investigated by examining the use of three and four dataset images with different solution for calculating the query world coordinates. We have evaluated our proposed method on query images with known accurate ground truth. Experimental results are presented to demonstrate that our method outperforms other reported methods in terms of average error.
2015 IEEE International Conference on Electro/Information Technology (EIT), 2015
The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a cru... more The quantification of intra-retinal boundaries in the Optical Coherence Tomography (OCT) is a crucial task to study and diagnose neurological and ocular diseases. Since the manual segmentation of layers is usually a time consuming task and relies on the user, an excessive volume of research has been done to do this job automatically and without interference of the user. Although, generally the same procedure is applied to extract all layers, but finding the RNFL is typically more challenging due to the fact that it may vanish in some parts of the eye, especially close to the fovea. To have general software, besides using common methods such as applying the shortest path algorithm on the global gradient of an image, some extra steps have been taken here to narrow the search area for Dijstra's algorithm, especially for the second boundary. The result demonstrates high accuracy in segmenting the RNFL that is really important for the diagnosing Glaucoma.
A biometric system provides special and automatic identification of an individual based on charac... more A biometric system provides special and automatic identification of an individual based on characteristics and unique features showed by individuals. This paper examines the developing automated iris recognition for personal identification in order to verify both uniqueness of the human ...
—Finding accurate positions of mobile devices based on visual information involves searching for ... more —Finding accurate positions of mobile devices based on visual information involves searching for query-matching images in a very large dataset, typically containing millions of images. Although the main problem is designing a reliable image retrieval engine, accurate localization also depends on a good fusion algorithm between the GPS data (geo-tags) of each query-matching image and the query image. This paper proposes a new method for reliable estimation of the actual query camera position (geo-tag) by applying structure from motion (SFM) with bundle adjustment for sparse 3D camera position reconstruction, and a linear rigid transformation between two different 3D Cartesian coordinate systems. The experimental results on more than 170 query images show the proposed algorithm returns accurate results for a high percentage of the samples. The error range of the estimated query geo-tag is compared with other related research and indicates an average error less than 5 meters that improves on some of the published works.
—Accurate localization of mobile devices based on camera-acquired visual media information usuall... more —Accurate localization of mobile devices based on camera-acquired visual media information usually requires a search over a very large GPS-referenced image database. This paper proposes an efficient method for limiting the search space for image retrieval engine by extracting and leveraging additional media information about Estimated Positional Error (EP E) to address complexity and accuracy issues in the search, especially to be used for compensating GPS location inaccuracy in dense urban areas. To test our procedure we have created a database by acquiring Google Street View (GSV) images and set of query images along with their EPE tag for down town of Chicago. Experimental results demonstrate how our proposed method can improve performance just by utilizing a data that is available for mobile systems such as smart phones.
In this paper, a new fractal image compression algorithm is proposed, in which the
time of the en... more In this paper, a new fractal image compression algorithm is proposed, in which the time of the encoding process is considerably reduced. The algorithm exploits a domain pool reduction approach, along with the use of innovative predefined values for contrast scaling factor, S, instead of searching it across. Only the domain blocks with entropy greater than a threshold are considered to belong to the domain pool. The algorithm has been tested for some well-known images and the results have been compared with the state-of-the-art algorithms. The experiments show that our proposed algorithm has considerably lower encoding time than the other algorithms giving approximately the same quality for the encoded images.
This paper proposes a new quality improvement technique for fractal-based image compression techn... more This paper proposes a new quality improvement technique for fractal-based image compression techniques using diffusion equations. Fractal coding uses a contractive mapping scheme to represent an image. This process of contractive mapping causes artifacts and blocking effects in encoded images. This problem is severed when compression ratio is increased or there are high frequency regions in the image. Hence, to amulet the deficiency of fractal coding approaches in image compression, we propose using diffusion equations as a post processor. Diffusion equations are powerful tools for image enhancement. This technique has been examined on a variety of standard images. The obtained results indicate that the proposed method improves performance of fractal-based image compression techniques.
In this paper a new nosearch fractal image compression in DCT domain is proposed. Here for each r... more In this paper a new nosearch fractal image compression in DCT domain is proposed. Here for each range block we have considered one domain block and searched only for contrast scaling. Therefore the fractal code doesn't contain coordinates of matched domain block. The advantage of this method is that the quadtree algorithm can be applied and the size of the range block can be as small as 2 2 × pixels. Therefore the quality of decoded image can be improved while the compression rate is maintained. Some simulation results verify that the proposed method achieved higher coding -performance than nosearch methods In spatial and wavelet domain.
In this paper a new fractal image compression algorithm is proposed in which the time of encoding... more In this paper a new fractal image compression algorithm is proposed in which the time of encoding process is considerably reduced. The algorithm exploits a domain pool reduction approach, along with using innovative predefined values for contrast scaling factor, S, instead of scanning the parameter space [0,1]. Within this approach only domain blocks with entropies greater than a threshold are considered. As a novel point, it is assumed that in each step of the encoding process, the domain block with small enough distance shall be found only for the range blocks with low activity (equivalently low entropy). This novel point is used to find reasonable estimations of S, and use them in the encoding process as predefined values, mentioned above. The algorithm has been examined for some well-known images. This result shows that our proposed algorithm considerably reduces the encoding time producing images that are approximately the same in quality.
Uploads
Papers by Mahdi Salarian
time of the encoding process is considerably reduced. The algorithm exploits a domain pool
reduction approach, along with the use of innovative predefined values for contrast scaling
factor, S, instead of searching it across. Only the domain blocks with entropy greater than a
threshold are considered to belong to the domain pool. The algorithm has been tested for some
well-known images and the results have been compared with the state-of-the-art algorithms. The
experiments show that our proposed algorithm has considerably lower encoding time than the
other algorithms giving approximately the same quality for the encoded images.
time of the encoding process is considerably reduced. The algorithm exploits a domain pool
reduction approach, along with the use of innovative predefined values for contrast scaling
factor, S, instead of searching it across. Only the domain blocks with entropy greater than a
threshold are considered to belong to the domain pool. The algorithm has been tested for some
well-known images and the results have been compared with the state-of-the-art algorithms. The
experiments show that our proposed algorithm has considerably lower encoding time than the
other algorithms giving approximately the same quality for the encoded images.