Poorna Banerjee Dasgupta

Poorna Banerjee Dasgupta

Image blurring refers to the degradation of an image wherein the image's overall sharpness decreases. Image blurring is caused by several factors. Additionally, during the image acquisition process, noise may get added to the image. Such a noisy and blurred image can be represented as the image resulting from the convolution of the original image with the associated point spread function, along with additive noise. However, the blurred image often contains inadequate information to uniquely determine the plausible original image. Based on the availability of blurring information, image deblurring methods can be classified as blind and non-blind. In non-blind image deblurring, some prior information is known regarding the corresponding point spread function and the added noise. The objective of this study is to determine the effectiveness of non-blind image deblurring methods with respect to the identification and elimination of noise present in blurred images. In this study, three non-blind image deblurring methods, namely Wiener deconvolution, Lucy-Richardson deconvolution, and regularized deconvolution were comparatively analyzed for noisy images featuring salt-and-pepper noise. Two types of blurring effects were simulated, namely motion blurring and Gaussian blurring. The said three non-blind deblurring methods were applied under two scenarios: direct deblurring of noisy blurred images and deblurring of images after denoising through the application of the adaptive median filter. The obtained results were then compared for each scenario to determine the best approach for deblurring noisy images.

Poorna Banerjee Dasgupta

The ability to modulate vocal sounds and generate speech is one of the features which set humans apart from other living beings. The human voice can be characterized by several attributes such as pitch, timbre, loudness, and vocal tone. It has often been observed that humans express their emotions by varying different vocal attributes during speech generation. Hence, deduction of human emotions through voice and speech analysis has a practical plausibility and could potentially be beneficial for improving human conversational and persuasion skills. This paper presents an algorithmic approach for detection and analysis of human emotions with the help of voice and speech processing. The proposed approach has been developed with the objective of incorporation with futuristic artificial intelligence systems for improving human-computer interactions.

Poorna Banerjee Dasgupta

Video watermarking is extensively used in many media-oriented applications for embedding watermarks, i.e. hidden digital data, in a video sequence to protect the video from illegal copying and to identify manipulations made in the video. In case of an invisible watermark, the human eye can not perceive any difference in the video, but a watermark extraction application can read the watermark and obtain the embedded information. Although numerous methodologies exist for embedding watermarks, many of them have shortcomings with respect to performance efficiency, especially over a distributed network. This paper proposes and analyses a 2-bit Least Significant Bit (LSB) parallel algorithmic approach for achieving performance efficiency to watermark and distribute videos over a client-server framework.

Poorna Banerjee Dasgupta

Edge detection is one of the most principal techniques for detecting discontinuities in the gray levels of image pixels. The Modulation Transfer Function (MTF) is one of the main criteria for assessing imaging quality and is a parameter frequently used for measuring the sharpness of an imaging system. In order to determine the MTF, it is essential to determine the best edge from the target image so that an edge profile can be developed and then the line spread function and hence the MTF, can be computed accordingly. For regular image sizes, the human visual system is adept enough to identify suitable edges from the image. But considering huge image datasets, such as those obtained from satellites, the image size may range in few gigabytes and in such a case, manual inspection of images for determination of the best suitable edge is not plausible and hence, edge profiling tasks have to be automated. This paper presents a novel, yet simple, algorithm for edge ranking and detection from image data-sets for MTF computation, which is ideal for automation on vectorised graphical processing units.

Poorna Banerjee Dasgupta

Noise removal from images is a part of image restoration in which we try to reconstruct or recover an image that has been degraded by using apriori knowledge of the degradation phenomenon. Noises present in images can be of various types with their characteristic Probability Distribution Functions (PDF). Noise removal techniques depend on the kind of noise present in the image rather than on the image itself. This paper explores the effects of applying noise reduction filters having similar properties on noisy images with emphasis on Signal-to-Noise-Ratio (SNR) value estimation for comparing the results.