Chintan K. Modi

CT Image Compression Using Compressive Sensing and Wavelet Transform

Compressive sensing (CS) technique addresses the issue of compressing the sparse signal with a rate below Nyquist rate of sampling. For medical images there are always issues of acquisition time and compression, the compressive sensing is found to be a better technique that works in a manner that it first acquires samples less than signal dimensionality and reconstructs the same signal. In this paper Wavelet transform is applied along with compressive sensing on CT images. Three various measurements (for three compression ratio values) have been taken and calculated PSNR, CoC, and RMSE. As measurements are increased PSNR, CoC and visual quality increases and RMSE decreases. The main observation is that only 60% measurements can reproduce image with PSNR of more than 25 dB and with CoC more than 0.99.

An Effective Iterative Back Projection Based Single Image Super Resolution Approach

In this paper, an effort is made to enlarge a low resolution image. This paper presents an effective novel single image super resolution approach to recover a high resolution image from a single low resolution input image. The approach is based on an Iterative back projection (IBP) method combined with the Canny Edge Detection and error difference image to recover high frequency information. This method is applied on different natural gray images and compared with different existing image super resolution approaches. Simulation results show that the proposed algorithm can more accurately enlarge the low resolution image than previous approaches. Proposed algorithm increases the PSNR and decreases MSE and MAE compared to other existing algorithms and also improves visual quality of an image considerably.

Non-destructive quality evaluation in spice industry with specific reference To Cuminum cyminum L (cumin) seeds

The Indian spice industry by and large is primitive yet. Screen cleaner and dust removing are the only operations which are being done alone in the industry. Quality assessment of spices is a very big challenge since time immemorial. In addition to inherent and hygienic features quality depends on its physical appearance, moisture content, composition which may be reflected by taste and smell too. Human sensory panel generally assess quality and such process is time consuming, unreliable and non reproducible. There is a need for some non invasive quality testing methodologies. This paper proposes a new method for counting the number of Cuminum cyminum L (cumin seeds)with long pedestals as well as foreign elements using machine vision non destructive technique based on combined measurements.

Comparison of Optimal Edge Detection Algorithms for Liquid Level Inspection in Bottles

In this paper few optimal edge detection techniques, used to inspect the over and under fill liquid level of bottle in machine vision system are compared. The text represents the steps and approaches for the inspection of over and under filled level in the bottle which would not only be helpful for quality inspection but in precised time too using different edge detection techniques. The results of Different optimal edge detection algorithm such as Marr- Hilderth LoG algorithm, Canny algorithm and Shen Castan algorithm were found to be much better than the traditional template based methods like Sobel and Kirsch operators.

ECG signal compression using Compressive Sensing and wavelet transform

Compressed Sensing (CS) is a novel approach of reconstructing a sparse signal much below the significant Nyquist rate of sampling. Due to the fact that ECG signals can be well approximated by the few linear combinations of wavelet basis, this work introduces a comparison of the reconstructed 10 ECG signals based on different wavelet families, by evaluating the performance measures as MSE (Mean Square Error), PSNR (Peak Signal To Noise Ratio), PRD (Percentage Root Mean Square Difference) and CoC (Correlation Coefficient). Reconstruction of the ECG signal is a linear optimization process which considers the sparsity in the wavelet domain. L1 minimization is used as the recovery algorithm. The reconstruction results are comprehensively analyzed for three compression ratios, i.e. 2:1, 4:1, and 6:1. The results indicate that reverse biorthogonal wavelet family can give better results for all CRs compared to other families.

Human Identification by Partial Iris Segmentation Using Pupil Circle Growing Based on Binary Integrated Edge Intensity Curve

Identification of human based on iris has gained increased attention in recent years. The paper focuses on novel and efficient approach of partial iris based recognition of human using pupil circle region growing and binary integrated edge intensity curve which defeats the difficulties of eyelids occlusions. The experimental results are obtained on CASIA database version-1 and show good performance with EER of 5.14%. The advantage of the proposed approach is its computational simplicity and good recognition accuracy as it avoids the eyelids portion from the iris region for further processing.

Hybrid Approach for Single Image Super Resolution Using ISEF and IBP

This paper addresses the problem of recovering a super-resolved image from a single low resolution input. This is a hybrid approach of single image super resolution. The technique is based on combining an Iterative back projection (IBP) method with the edge preserving Infinite symmetrical exponential filter (ISEF). Though IBP can minimize the reconstruction error significantly in iterative manner and gives good result, it suffers from ringing effect and chessboard effect because error is back-projected without edge guidance. ISEF provides edge-smoothing image by adding high frequency information. Proposed algorithm integrates ISEF with IBP which improves visual quality with very fine edge details. The method is applied on different type of images including face image, natural image and medical image, the performance is compared with a number of other algorithms, bilinear interpolation, nearest neighbor interpolation and Laplacian of Gaussian (LOG). The method proposed in the paper is shown to be marginally superior to the existing method in terms of visual quality and peak signal to noise ratio (PSNR).

A simple and novel algorithm for automatic selection of ROI for dental radiograph segmentation

Segmentation of dental X-ray image helps to find two major regions of dental X-ray image: 1) gap valley, 2) tooth isolation. Dental radiograph segmentation is a challenging problem because of intensity variation and noise. Traditional algorithms make use of gray and binary intensity integral curves. Using these curves the regions of gap valley and tooth isolation are extracted. We propose a novel method of finding ROI for both gap valley and tooth isolation using binary edge intensity integral curves. The proposed algorithm uses region growing approach followed by Canny edge detector. It automatically finds the ROI both for gap valley and tooth isolation in 83% dental radiograph images without rotation.

Image morphological operation based quality analysis of coriander seed (Coriandrum satavum L)

The paper presents a solution for quality evaluation and grading of spice food industry using computer vision and image processing. In this paper basic problem of Indian spice industry for quality assessment is defined which is traditionally done manually by human inspector. This method is time consuming as well as costly. With the help of proposed method for solution of quality assessment via computer vision, image analysis and processing a fast and accurate quality evaluation is achieved. In this paper we propose a method for counting the number of Coriandrum sativum L (coriander seeds) with long pedestals as well as foreign elements using image processing with a high degree of quality and then quantify the quality of the coriander seeds.

Selecting the Most Favorable Wavelet for Compressing ECG Signals Using Compressive Sensing Approach

Compressed Sensing (CS) is a novel approach of reconstructing a sparse signal much below the significant Nyquist rate of sampling. Due to the fact that ECG signals can be well approximated by the few linear combinations of wavelet basis, this work introduces a comparison of the reconstructed ECG signal based on different wavelet families, by evaluating the performance measures as MSE (Mean Square Error), PSNR (Peak Signal To Noise Ratio), PRD (Percentage Root Mean Square Difference) and CoC (Correlation Coefficient). Reconstruction of the ECG signal is a linear optimization process which consider the sparsity in the wavelet domain, perceived by the fact that higher the sparsity, more better the recovery. L1 minimization is used as the recovery algorithm. The reconstruction results are comprehensively analyzed for five compression ratios, i.e. 2:1, 4:1, 6:1, 8:1 and 10:1. The results indicate that reverse biorthogonal wavelet family can give better results for all (Compression Ratios)CRs compared to other families.