Jayanta Mukherjee

Enhancement of Color Images by Scaling the DCT Coefficients

This paper presents a new technique for color enhancement in the compressed domain. The proposed technique is simple but more effective than some of the existing techniques reported earlier. The novelty lies in this case in its treatment of the chromatic components, while previous techniques treated only the luminance component. The results of all previous techniques along with that of the proposed one are compared with respect to those obtained by applying a spatial domain color enhancement technique that appears to provide very good enhancement. The proposed technique, computationally more efficient than the spatial domain based method, is found to provide better enhancement compared to other compressed domain based approaches.

New efficient methods of image compression in digital cameras with color filter array

Many consumer digital color cameras use a single light sensitive sensor and a color filter array (CFA) with each pixel element recording intensity information of one color component. The captured data is interpolated into a full color image, which is then compressed in many applications. Carrying out color interpolation before compression introduces redundancy in the data. In this paper we discuss methods and issues involved in the compression of CFA data before full color interpretation. The compression methods described operate on the same number of pixels as the sensor data. To obtain improved image quality, median filtering is applied as post-processing. Furthermore, to assure low complexity, the CFA data is compressed by JPEG. Simulations have demonstrated that substantial improvement in image quality is achievable using these new schemes.

Image resizing in the compressed domain using subband DCT

Resizing of digital images is needed in various applications, such as transmission of images over communication channels varying widely in their bandwidths, display at different resolutions depending on the resolution of a display device, etc. In this work, we propose a modification of a recently proposed elegant image resizing algorithm by Dugad and Ahuja (2001). We have also extended their approach and our modified versions to color images and studied their performance at different levels of compression for an image. Our proposed modified algorithms, in general, perform better than the earlier method in most cases. Though there is a marginal increase in the computation required in image-halving, the computation overhead of the proposed modification is higher compared to the Dugad-Ahuja algorithm in the case of doubling the images.

Gait recognition using Pose Kinematics and Pose Energy Image

Many of the existing gait recognition approaches represent a gait cycle using a single 2D image called Gait Energy Image (GEI) or its variants. Since these methods suffer from lack of dynamic information, we model a gait cycle using a chain of key poses and extract a novel feature called Pose Energy Image (PEI). PEI is the average image of all the silhouettes in a key pose state of a gait cycle. By increasing the resolution of gait representation, more detailed dynamic information can be captured. However, processing speed and space requirement are higher for PEI than the conventional GEI methods. To overcome this shortcoming, another novel feature named as Pose Kinematics is introduced, which represents the percentage of time spent in each key pose state over a gait cycle. Although the Pose Kinematics based method is fast, its accuracy is not very high. A hierarchical method for combining these two features is, therefore, proposed. At first, Pose Kinematics is applied to select a set of most probable classes. Then, PEI is used on these selected classes to get the final classification. Experimental results on CMUs Mobo and USFs HumanID data set show that the proposed approach outperforms existing approaches.

Graph-Based Multiplayer Detection and Tracking in Broadcast Soccer Videos

In this paper, we propose a graph-based approach for detecting and tracking multiple players in broadcast soccer videos. In the first stage, the position of the players in each frame is determined by removing the non player regions. The remaining pixels are then grouped using a region growing algorithm to identify probable player candidates. A directed weighted graph is constructed, where probable player candidates correspond to the nodes of the graph while each edge links candidates in a frame with the candidates in next two consecutive frames. Finally, dynamic programming is applied to find the trajectory of each player. Experiments with several sequences from broadcasted videos of international soccer matches indicate that the proposed approach is able to track the players reasonably well even under varied illumination and ground conditions.

Metricity of super-knight's distance in digital geometry

Abstract In this paper we have extended the knights moves in chess to introduce super-knights moves in digital geometry. They define super-knights distance (like the knights distance [1]). However, all super-knights distances are not metrics. We have proved a theorem to show that a super-knights distance is a metric if and only if the underlying super-knights move is well-behaved in a specific sense. We conclude with suggestions on future study.

On connectivity issues of ESPTA

Abstract In this paper we review the connectivity properties of our 3-D thinning algorithm ESPTA (Extended Safe Point Thinning Algorithm [2]) and its other versions. We present a modification of ESPTA, called MESPTA, which preserves the connectivity of the image while maintaining its 3-D shape.

MRF Clustering for segmentation of color images

In this paper a segmentation algorithm has been described based on Markov Random Field (MRF) processing. The images are segmented initially by growing regions of similar color values. Then a general framework for refining initial clusters in a feature space using MRF processing is presented and subsequently, the algorithm for MRF processing in the color spaces is proposed. The proposed MRF processing is shown to be working with the principles of 1-NN and K-NN classification rules among the neighbors of a pixel. This has remarkably improved the initial segmentation results. The segmentation algorithm in this work, first, uses only the chromatic information. Then experimentations using all the three color components (i.e. with the inclusion of luminance factors also) are also presented. It has been observed that, though using only chromatic information good segmentation results are obtained, the luminance information improves the quality of segmentation in some cases. Results for different color spaces such as the OHTA coordinate space (referred to as the OHTA space in the present work), YIQ, CIELAB and UVW are also presented here. On the average the performance in the OHTA space is found to be better than the others.

Markov random field processing for color demosaicing

Abstract In digital color imaging, color filter arrays (CFAs) are obtained from single-chip cameras in the form of sampled spectral components (red, green and blue) in an interleaved fashion. Color demosaicing is the process of interpolating these CFAs into dense pixel maps for each spectral component. There are different interpolation techniques for color demosaicing operations. These approaches have their limitations regarding the improvement of the quality of the images. Particularly, they perform poorly in recovering the edges of the images. In this work we have applied Markov random field (MRF) processing over these roughly interpolated images obtained by the existing techniques to improve the quality of the reconstruction. We have observed that the processing improves the image quality in many cases. Particularly, the edges of the reconstructed images are significantly enhanced using MRF processing.

On approximating Euclidean metrics by digital distances in 2D and 3D

Abstract In this paper a geometric approach is suggested to find the closest approximation to Euclidean metric based on geometric measures of the digital circles in 2D and the digital spheres in 3D for the generalized octagonal distances. First we show that the vertices of the digital circles (spheres) for octagonal distances can be suitably approximated as a function of the number of neighborhood types used in the sequence. Then we use these approximate vertex formulae to compute the geometric features in an approximate way. Finally we minimize the errors of these measurements with respect to respective Euclidean discs to identify the best distances. We have verified our results by experimenting with analytical error measures suggested earlier. We have also compared the performances of the good octagonal distances with good weighted distances. It has been found that the best octagonal distance in 2D ({1,1,2}) performs equally good with respect to the best one for the weighted distances (〈3,4〉). In fact in 3D, the octagonal distance {1,1,3} has an edge over the other good weighted distances.