Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708038
Gabriel Pablo Nava, Y. Kamamoto, Takashi G. Sato, Yoshifumi Shiraki, N. Harada, T. Moriya
Optical communication through light-emitting diodes (LEDs) and video cameras is rapidly gaining attention due to the increasing pervassiveness of those devices, and because of its potential data capacity. However, the communication quality is greatly compromised by the low resolution of the imaging sensor which produces blurred images of the LEDs at long distances. On the other hand, the images recorded at high frame rates possess particular features that can be used to improve the reception. This paper suggests image processing techniques to detect and decode the optical signals of an array of LEDs. For the case of blurred images, detection of the LED's is reinforced by a k-means clustering algorithm based on distance measurements derived from the linear correlation among pixel intensities along the time dimension. Experiments with a prototype show that the proposed algorithms can improve the bit error rate (BER) of the decoded signal. Furthermore, partial implementation on a General Purpose Graphics Processing Unit (GPGPU) is also addressed, and processing times are demonstrated.
{"title":"Image processing techniques for high speed camera-based free-field optical communication","authors":"Gabriel Pablo Nava, Y. Kamamoto, Takashi G. Sato, Yoshifumi Shiraki, N. Harada, T. Moriya","doi":"10.1109/ICSIPA.2013.6708038","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708038","url":null,"abstract":"Optical communication through light-emitting diodes (LEDs) and video cameras is rapidly gaining attention due to the increasing pervassiveness of those devices, and because of its potential data capacity. However, the communication quality is greatly compromised by the low resolution of the imaging sensor which produces blurred images of the LEDs at long distances. On the other hand, the images recorded at high frame rates possess particular features that can be used to improve the reception. This paper suggests image processing techniques to detect and decode the optical signals of an array of LEDs. For the case of blurred images, detection of the LED's is reinforced by a k-means clustering algorithm based on distance measurements derived from the linear correlation among pixel intensities along the time dimension. Experiments with a prototype show that the proposed algorithms can improve the bit error rate (BER) of the decoded signal. Furthermore, partial implementation on a General Purpose Graphics Processing Unit (GPGPU) is also addressed, and processing times are demonstrated.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130053730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707979
Dongdong Zhang, Ye Yao, D. Zang, Yanyu Chen
In this paper, we propose a spatio-temporal inpainting method to recover depth images generated by Kinect. Based on the assumption that neighbouring pixels similar in color are likely to have similar depth values, for the first depth image and the sub-images including the motion bodies extracted from the following depth frames, we use color segmentation maps of the corresponding color video frames to guide the depth filling. Considering that some dark regions without valid depth value could lead to the fail of color-segmentation based depth filling, we design a dark region detection method and further refine hole-filling of the unfilled regions with the valid depth values of the same dark region. For the static areas of Kinect depth video, the recovered depth at the same position of previous frame is used to recover the lost depth in the current depth frame. Experimental results show that the proposed method significantly improves depth quality by successfully filling the holes so that we can use it for better 3D rendering.
{"title":"A spatio-temporal inpainting method for Kinect depth video","authors":"Dongdong Zhang, Ye Yao, D. Zang, Yanyu Chen","doi":"10.1109/ICSIPA.2013.6707979","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707979","url":null,"abstract":"In this paper, we propose a spatio-temporal inpainting method to recover depth images generated by Kinect. Based on the assumption that neighbouring pixels similar in color are likely to have similar depth values, for the first depth image and the sub-images including the motion bodies extracted from the following depth frames, we use color segmentation maps of the corresponding color video frames to guide the depth filling. Considering that some dark regions without valid depth value could lead to the fail of color-segmentation based depth filling, we design a dark region detection method and further refine hole-filling of the unfilled regions with the valid depth values of the same dark region. For the static areas of Kinect depth video, the recovered depth at the same position of previous frame is used to recover the lost depth in the current depth frame. Experimental results show that the proposed method significantly improves depth quality by successfully filling the holes so that we can use it for better 3D rendering.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130514079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708006
S. Ramamurthy
We describe an efficient algorithm for rate control in JPEG2000 or similar sub-band based visual compression schemes. Operating in tandem with the compression process, our method initially predicts “Distortion-Rate” (RD) slopes for all code-blocks' coding data, based on empirical statistics of coefficients and subsequently uses a greedy approach. We use an optimized doubly-linked tree structure, which is initially constructed using predicted slopes as the key. The tree is subsequently updated with actual slopes to proceed with our rate allocation method. Our algorithm allows for fine-grain targeting of bitrates. A good balance of complexity and quality is observed in this scheme vis-à-vis the full effort Post Compression Rate Distortion (PCRD) optimization. Quality is optimized across a multitude of code-blocks competing for their constituent coding passes to be embedded into the bitstream, with good `dispersion' of distortion.
{"title":"Efficient, ‘greedy’ rate allocation for JPEG2000","authors":"S. Ramamurthy","doi":"10.1109/ICSIPA.2013.6708006","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708006","url":null,"abstract":"We describe an efficient algorithm for rate control in JPEG2000 or similar sub-band based visual compression schemes. Operating in tandem with the compression process, our method initially predicts “Distortion-Rate” (RD) slopes for all code-blocks' coding data, based on empirical statistics of coefficients and subsequently uses a greedy approach. We use an optimized doubly-linked tree structure, which is initially constructed using predicted slopes as the key. The tree is subsequently updated with actual slopes to proceed with our rate allocation method. Our algorithm allows for fine-grain targeting of bitrates. A good balance of complexity and quality is observed in this scheme vis-à-vis the full effort Post Compression Rate Distortion (PCRD) optimization. Quality is optimized across a multitude of code-blocks competing for their constituent coding passes to be embedded into the bitstream, with good `dispersion' of distortion.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114418936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707967
Dongdong Zhang, Lijing Gao, D. Zang, Yaoru Sun
Most of the traditional JND models in DCT domain compute the JND threshold by incorporating the spatial contrast sensitivity function, the luminance adaptation effect and the contrast masking effect. How to integrate visual attention effect into the traditional JND models is still an open problem. In this paper, we proposed a new DCT-domain JND profile, in which a combined modulation function is built, based on the image saliency and textural characteristic to describe the visual attention effect and contrast masking effect on JND Threshold in DCT domain. Experimental results show that the proposed model can tolerate more distortion with the same perceptual quality, compared with the latest DCT-domain JND model. In terms of PSNR, the improvement of tolerated distortion is 0.54dB on average.
{"title":"A DCT-domain JND model based on visual attention for image","authors":"Dongdong Zhang, Lijing Gao, D. Zang, Yaoru Sun","doi":"10.1109/ICSIPA.2013.6707967","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707967","url":null,"abstract":"Most of the traditional JND models in DCT domain compute the JND threshold by incorporating the spatial contrast sensitivity function, the luminance adaptation effect and the contrast masking effect. How to integrate visual attention effect into the traditional JND models is still an open problem. In this paper, we proposed a new DCT-domain JND profile, in which a combined modulation function is built, based on the image saliency and textural characteristic to describe the visual attention effect and contrast masking effect on JND Threshold in DCT domain. Experimental results show that the proposed model can tolerate more distortion with the same perceptual quality, compared with the latest DCT-domain JND model. In terms of PSNR, the improvement of tolerated distortion is 0.54dB on average.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123891860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708015
Nur Baiti Zahir, R. Samad, M. Mustafa
A face detection system is a computer application for automatically detecting a human face from digital image or video frame. This paper presents a face detection system that used web camera to detect and track a face in real-time. To detect a face in the image, a simple method of skin color detection is used. By using color detection method in this project, the face can be segmented easily from the complex background. However, to detect a face in real-time is quite challenging especially when a face is moving and the real-time environment has uneven illumination. This paper presents the preliminary result of face detection and tracking system, which is the system, detects a face that has different poses in a real-time situation, where the light condition is uneven. Here, to complete the detection process, contour detection method is added so that the detection is more accurate. This system can be applied in many applications such as banking system to reduce the number of forgery, security system, and human-computer interaction (HCI).
{"title":"Initial experimental results of real-time variant pose face detection and tracking system","authors":"Nur Baiti Zahir, R. Samad, M. Mustafa","doi":"10.1109/ICSIPA.2013.6708015","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708015","url":null,"abstract":"A face detection system is a computer application for automatically detecting a human face from digital image or video frame. This paper presents a face detection system that used web camera to detect and track a face in real-time. To detect a face in the image, a simple method of skin color detection is used. By using color detection method in this project, the face can be segmented easily from the complex background. However, to detect a face in real-time is quite challenging especially when a face is moving and the real-time environment has uneven illumination. This paper presents the preliminary result of face detection and tracking system, which is the system, detects a face that has different poses in a real-time situation, where the light condition is uneven. Here, to complete the detection process, contour detection method is added so that the detection is more accurate. This system can be applied in many applications such as banking system to reduce the number of forgery, security system, and human-computer interaction (HCI).","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126838487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708019
Nor Rashidah Md Juremi, M. A. Zulkifley, A. Hussain
Steady state visual evoked potential (SSVEP) is one of the BCI responses that is elicited from the external stimulus. SSVEP is a noisy signal that requires signal smoothing before any further processing can be performed. In this paper, we implement double exponential smoothing (DES) to minimize the ripple of SSVEP response in the frequency domain. The input signal was generated artificially by using trigonometric function (sine wave). Three fundamental frequencies were analyzed, which are 30, 15 and 7.5 Hz that are based on refresh rate of the stimulator. Euclidean distance (ED) technique is used as the evaluation metric to calculate the error between the results and ground truth. The results show that the smoothed signal by DES technique achieved a lower value of ED compared to the original signal.
{"title":"Smoothing the artificial SSVEP response using double exponential smoothing method","authors":"Nor Rashidah Md Juremi, M. A. Zulkifley, A. Hussain","doi":"10.1109/ICSIPA.2013.6708019","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708019","url":null,"abstract":"Steady state visual evoked potential (SSVEP) is one of the BCI responses that is elicited from the external stimulus. SSVEP is a noisy signal that requires signal smoothing before any further processing can be performed. In this paper, we implement double exponential smoothing (DES) to minimize the ripple of SSVEP response in the frequency domain. The input signal was generated artificially by using trigonometric function (sine wave). Three fundamental frequencies were analyzed, which are 30, 15 and 7.5 Hz that are based on refresh rate of the stimulator. Euclidean distance (ED) technique is used as the evaluation metric to calculate the error between the results and ground truth. The results show that the smoothed signal by DES technique achieved a lower value of ED compared to the original signal.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"3 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131957109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707971
Alfian Abdul Halin, N. Sharef, A. Jantan, L. N. Abdullah
This paper presents a probabilistic technique to localize license plates regions for cars adhering to the standard set by the Malaysian Road Transport Department. Images of the front/rear-view of cars displaying their license plates are firstly preprocessed, followed by features extraction generated from connected components analysis. These features are then used to train a Naïve Bayes classifier for the final task of license plates localization. Experimental results conducted on 144 images have shown that considering two candidates with the highest posterior probabilities better guarantees license plates regions are properly localized, with a recall of 0.98.
{"title":"License plate localization using a Naïve Bayes classifier","authors":"Alfian Abdul Halin, N. Sharef, A. Jantan, L. N. Abdullah","doi":"10.1109/ICSIPA.2013.6707971","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707971","url":null,"abstract":"This paper presents a probabilistic technique to localize license plates regions for cars adhering to the standard set by the Malaysian Road Transport Department. Images of the front/rear-view of cars displaying their license plates are firstly preprocessed, followed by features extraction generated from connected components analysis. These features are then used to train a Naïve Bayes classifier for the final task of license plates localization. Experimental results conducted on 144 images have shown that considering two candidates with the highest posterior probabilities better guarantees license plates regions are properly localized, with a recall of 0.98.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114857798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707984
H. Korkmaz, S. Alsan
In medical industry, studies about storing, processing, analyzing and re-accessing the patient's information and images are intensively continuing. Both printed and digital medical images take more spaces than the others. In this paper, a mechanism which transfers easily the printed X-ray images to the digital environment enabling radiological assessment and archiving is set and a software is developed to help the analysis of those images. It is aimed to digitize the conventional images with a minimum loss while keeping the image quality. The setup which is in a closed box consists of a light source, a camera for image transfer and lenses. The software provides applying the image processing algorithms on digitized images and archiving them in DICOM format.
{"title":"A low cost medical image digitization setup for enhancement and analyzing of conventional X-ray images","authors":"H. Korkmaz, S. Alsan","doi":"10.1109/ICSIPA.2013.6707984","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707984","url":null,"abstract":"In medical industry, studies about storing, processing, analyzing and re-accessing the patient's information and images are intensively continuing. Both printed and digital medical images take more spaces than the others. In this paper, a mechanism which transfers easily the printed X-ray images to the digital environment enabling radiological assessment and archiving is set and a software is developed to help the analysis of those images. It is aimed to digitize the conventional images with a minimum loss while keeping the image quality. The setup which is in a closed box consists of a light source, a camera for image transfer and lenses. The software provides applying the image processing algorithms on digitized images and archiving them in DICOM format.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124085042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708030
F. Motlagh, S. Tang, O. Motlagh
Single-trail detection of P300 from EEG signals is the main challenge of diagnostic purposes and research applications. In this article, Wavelet Transform is used for feature extraction from EEG signals. The goal is to prove the capability of wavelet transform in P300 feature extraction. A number of established wavelet feature extraction methods were evaluated from accuracy and computation speed perspectives. To conduct uniform evaluation, Support Vector Machine (SVM) was used for classification of all methods. The results show that DWT can be fast in computing signal features with lower accuracy, while a combination of DWT and T-CWT is proven to be more accurate when real-time computation is concerned.
{"title":"Optimal accuracy and runtime trade-off in wavelet based single-trial P300 detection","authors":"F. Motlagh, S. Tang, O. Motlagh","doi":"10.1109/ICSIPA.2013.6708030","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708030","url":null,"abstract":"Single-trail detection of P300 from EEG signals is the main challenge of diagnostic purposes and research applications. In this article, Wavelet Transform is used for feature extraction from EEG signals. The goal is to prove the capability of wavelet transform in P300 feature extraction. A number of established wavelet feature extraction methods were evaluated from accuracy and computation speed perspectives. To conduct uniform evaluation, Support Vector Machine (SVM) was used for classification of all methods. The results show that DWT can be fast in computing signal features with lower accuracy, while a combination of DWT and T-CWT is proven to be more accurate when real-time computation is concerned.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126272297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-08-01DOI: 10.1109/ICSIPA.2013.6708017
K. Hasikin, N. Isa
This paper presents the fuzzy image enhancement for low contrast and non-uniform illumination images. A new fuzzy intensity measure is proposed to distinguish between the dark and bright regions. This measure is computed by considering the average intensity and deviation of the intensity distribution of the image. The input image is enhanced using a power-law transformation. Implementation of the proposed algorithm on the non-uniform illumination and low contrast images show that the proposed algorithm outperforms the other enhancement techniques. The proposed algorithm produces more even illumination with improvement in the details and contrasts. In addition, the proposed algorithm is computationally fast to be implemented in real time application.
{"title":"Fuzzy image enhancement for low contrast and non-uniform illumination images","authors":"K. Hasikin, N. Isa","doi":"10.1109/ICSIPA.2013.6708017","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708017","url":null,"abstract":"This paper presents the fuzzy image enhancement for low contrast and non-uniform illumination images. A new fuzzy intensity measure is proposed to distinguish between the dark and bright regions. This measure is computed by considering the average intensity and deviation of the intensity distribution of the image. The input image is enhanced using a power-law transformation. Implementation of the proposed algorithm on the non-uniform illumination and low contrast images show that the proposed algorithm outperforms the other enhancement techniques. The proposed algorithm produces more even illumination with improvement in the details and contrasts. In addition, the proposed algorithm is computationally fast to be implemented in real time application.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132881884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：