Brain tumor is one of the leading causes of death in humans worldwide. Image recognition or computer vision uses deep learning based approaches for automatic tumor detection by classifying brain images. It is difficult to analyze the similarity between brain tissues while processing the magnetic resonance imaging (MRI) brain images for tumor classification. In this paper, residual network-152 (ResNet-152) with softmax layer is proposed for accurate detection of brain tumor with low complexity. Initially, the brain images are pre-processed and segmented with adaptive canny mayfly algorithm (ACMA). More discriminative features are extracted from the pre-processed image with spatial gray level dependence matrix (SGLDM), and optimal features are selected with modified chimpanzee optimization algorithm (MChOA). The optimal feature selection and optimal performance of classification are obtained by eliminating poor generalization and over specialization. After eliminating redundancies, the features are fed to residual classification. The overall performance of the proposed tumor classification method is evaluated using various parameters such as accuracy, precision, recall, F-score, MCC and balanced accuracy. The evaluation results indicate that our proposed method reached the accuracy level of 98.85%, which is efficient than other conventional approaches such as convolutional neural network (CNN), ResNet, recurrent neural network (RNN), random belief network (RBN), liner support vector machine (LSVM) and poly-SVM.

This paper presents a novel approach for rationalization of irrational coefficients of filters designed using three-step lifting scheme. The existing three-step lifting schemes result in the irrational filter coefficients which require infinite precision for implementation. In this work, Euler-Frobenius halfband polynomials are designed to obtain the required kernels of three-step lifting structure. Next, the efficient rationalization of the designed filter banks (FBs) is proposed to reduce the arithmetic complexity. The proposed rational FBs preserve perfect reconstruction, near-orthogonality and regularity properties of wavelet FBs. These filters with rational coefficients are then used in image compression algorithms to compress the test images in well-known Classic, EPFL, RAISE, FiveK datasets and chromosome image datasets. The performance of the proposed rational FBs is compared with the existing rational FBs. It is observed that the performance of the proposed rational FBs is improved in terms of computational cost, encoding-decoding time and compression ratio as compared to existing rational FBs.

In this paper, we present a novel approach for the design of 9/7 near-perfect-reconstruction wavelets that are efficient for image compression. These wavelets have maximum vanishing moments for both decomposition and reconstruction filters. Among the existing 9/7 tap wavelet filters, the Cohen-Daubechies-Feauveau (CDF) 9/7 are known to have the largest regularity. However, these wavelets have irrational coefficients thus requiring infinite precision implementation. Unlike state- of-art designs that compromise vanishing moments for attaining low-complexity coefficients, our algorithm ensures both. We start with a spline function of length 5 and select the remaining factors to obtain wavelets with rationalized coefficients. By proper choice of design parameters, it is possible to find very low complexity dyadic wavelets with compact support.We suggest a near half band criterion to attain a suitable combination of low-pass analysis and decomposition filters. The designed filter bank is found to give significant hardware advantage as compared with existing filter pairs. Moreover, these low-complexity wavelets have characteristics similar to standard (CDF 9/7) wavelets. The designed wavelets are tested for their suitability in applications such as image compression. Simulations results depict that the designed wavelets give comparable performances on most of the benchmark images. Subsequently, they can be used in applications that require fewer computations and lesser hardware.

This paper addresses the construction of a family of wavelets based on halfband polynomials. An algorithm is proposed that ensures maximum zeros at ω = π for a desired length of analysis and synthesis filters. We start with the coefficients of the polynomial (x+1)(n) and then use a generalized matrix formulation method to construct the filter halfband polynomial. The designed wavelets are efficient and give acceptable levels of peak signal-to-noise ratio when used for image compression. Furthermore, these wavelets give satisfactory recognition rates when used for feature extraction. Simulation results show that the designed wavelets are effective and more efficient than the existing standard wavelets.

Abstract-This paper presents a shift, scale, and rotation-in- variant technique for iris feature-representation and fused postclassification at the decision-level to improve the accuracy and speed of the iris-recognition system. Most of the iris-recognition systems are still incapable for providing low false rejections due to a wide variety of artifacts and are computationally inefficient. In order to address these problems, effective and computationally efficient iris features are extracted based on a new class of triplet half-band filter bank (THFB). First, a new class of THFB is designed by using generalized half-band polynomial suitable for iris feature extraction. This THFB satisfies perfect reconstruction (PR) and provides linear phase, regularity, better frequency-selectivity, near-orthogonality, and good time-frequency localization. The uses of these properties are investigated to approximate iris features significantly. Second, a novel flexible k-out-of-n.A (Accept) postclassifier (any k-out-of-n-regions-Accept) is explored to achieve the robustness against possible intraclass iris variations. The proposed approach (THFB+ k-out-of-n.A) is capable of handling various artifacts, particularly segmentation error, eyelid/eyelashes occlusion, shadow of eyelids, head-tilt, and specular reflections during iris verification. Experimental results using UBIRIS, MMU1, CASIA-IrisV3, and IITD databases show the superiority of the proposed approach with some of the existing popular iris-recognition algorithms.