LOCAL FEATURE EXTRACTION IN IMAGES

The methods of the local feature point extraction are analyzed. The analysis shows that the most effective detectors are based on the brightness gradient determination. They usually use the Harris angle detector, which is complex in calcu­la­tions. The algorithm complexity minimization contradicts both the detector effective­ness and to the high dynamic range of the analyzed image. As a result, the high-speed methods could not recognize the feature points in the heavy luminance conditions. The modification of the high dynamic range (HDR) image compression algorithm based on the Retinex method is proposed. It contains an adaptive filter, which preserves the image edges. The filter is based on a set of feature detectors perfor­ming the Harris-Laplace transform which is much simpler than the Harris angle detector. A prototype of the HDR video camera is designed which provides sharp images. Its structure simplifies the design of the artificial intelligence engine, which is implemented in FPGA of medium or large size.

An Early Breast Cancer Detection System Using Recurrent Neural Network (RNN) with Animal Migration Optimization (AMO) Based Classification Method

Breast cancer can be detected using early signs of it mammograms and digital mammography. For Computer Aided Detection (CAD), algorithms can be developed using this opportunities. Early detection is assisted by self-test and periodical check-ups and it can enhance the survival chance significantly. Due the need of breast cancer’s early detection and false diagnosis impact on patients, made researchers to investigate Deep Learning (DL) techniques for mammograms. So, it requires a non-invasive cancer detection system, which is highly effective, accurate, fast as well as robust. Proposed work has three steps, (i) Pre-processing, (ii) Segmentation, and (iii) Classification. Firstly, preprocessing stage removing noise from images by using mean and median filtering algorithms are used, while keeping its features intact for better understanding and recognition, then edge detection by using canny edge detector. It uses Gaussian filter for smoothening image. Gaussian smoothening is used for enhancing image analysis process quality, result in blurring of fine-scaled image edges. In the next stage, image representation is changed into something, which makes analyses process as a simple one. Foreground and background subtraction is used for accurate breast image detection in segmentation. After completion of segmentation stage, the remove unwanted image in input image dataset. Finally, a novel RNN forclassifying and detecting breast cancer using Auto Encoder (AE) based RNN for feature extraction by integrating Animal Migration Optimization (AMO) for tuning the parameters of RNN model, then softmax classifier use RNN algorithm. Experimental results are conducted using Mini-Mammographic (MIAS) dataset of breast cancer. The classifiers are measured through measures like precision, recall, f-measure and accuracy.

The lower bound of nonlocal gradient for non-convex and non-smooth image patches based regularization

In the inverse problem of image processing, we have witnessed that the non-convex and non-smooth regularizers can produce clearer image edges than convex ones such as total variation (TV). This fact can be explained by the uniform lower bound theory of the local gradient in non-convex and non-smooth regularization. In recent years, although it has been numerically shown that the nonlocal regularizers of various image patches based nonlocal methods can recover image textures well, we still desire a theoretical interpretation. To this end, we propose a non-convex non-smooth and block nonlocal (NNBN) regularization model based on image patches. By integrating the advantages of the non-convex and non-smooth potential function in the regularization term, the uniform lower bound theory of the image patches based nonlocal gradient is given. This approach partially explains why the proposed method can produce clearer image textures and edges. Compared to some classical regularization methods, such as total variation (TV), non-convex and non-smooth (NN) regularization, nonlocal total variation (NLTV) and block nonlocal total variation(BNLTV), our experimental results show that the proposed method improves restoration quality.

A second-order nonlocal regularized variational model for multiframe image super-resolution

In this paper, we propose a new nonlocal super-resolution (SR) model which is a combination of the nonlocal total variation (TV) regularization and the nonlocal p-Laplacian term (with p = 2). This choice is motivated by the success of the nonlocal TV term in preserving image edges and the efficiency of the nonlocal p-Laplacian term in preserving the image texture. To ensure the convergence of the proposed optimization SR problem, we prove the existence and uniqueness of a solution in a well-posed framework. In addition, to resolve the encountered minimization problem, we proposed a modified primal-dual algorithm and numerical results are also given to show the performance of the proposed approach.

Deblurring Turbulent Images via Maximizing L1 Regularization

Atmospheric turbulence significantly degrades image quality. A blind image deblurring algorithm is needed, and a favorable image prior is the key to solving this problem. However, the general sparse priors support blurry images instead of explicit images, so the details of the restored images are lost. The recently developed priors are non-convex, resulting in complex and heuristic optimization. To handle these problems, we first propose a convex image prior; namely, maximizing L1 regularization (ML1). Benefiting from the symmetrybetween ML1 and L1 regularization, the ML1 supports clear images and preserves the image edges better. Then, a novel soft suppression strategy is designed for the deblurring algorithm to inhibit artifacts. A coarse-to-fine scheme and a non-blind algorithm are also constructed. For qualitative comparison, a turbulent blur dataset is built. Experiments on this dataset and real images demonstrate that the proposed method is superior to other state-of-the-art methods in blindly recovering turbulent images.

Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images

The convolutional neural network has achieved good results in the superresolution reconstruction of single-frame images. However, due to the shortcomings of infrared images such as lack of details, poor contrast, and blurred edges, superresolution reconstruction of infrared images that preserves the edge structure and better visual quality is still challenging. Aiming at the problems of low resolution and unclear edges of infrared images, this work proposes a two-stage generative adversarial network model to reconstruct realistic superresolution images from four times downsampled infrared images. In the first stage of the generative adversarial network, it focuses on recovering the overall contour information of the image to obtain clear image edges; the second stage of the generative adversarial network focuses on recovering the detailed feature information of the image and has a stronger ability to express details. The infrared image superresolution reconstruction method proposed in this work has highly realistic visual effects and good objective quality evaluation results.

Single-Image Super-Resolution Using Panchromatic Gradient Prior and Variational Model

Single-image super-resolution (SISR) is a resolution enhancement technique and is known as an ill-posed problem. Motivated by the idea of pan-sharping, we propose a novel variational model for SISR. The structure tensor of the input low-resolution image is exploited to obtain the gradient of an imaginary panchromatic image. Then, by constraining the gradient consistency, the image edges and details can be better recovered during the procedure of restoration of high-resolution images. Besides, we resort to the nonlocal sparse and low-rank regularization of image patches to further improve the super-resolution performance. The proposed variational model is efficiently solved by ADMM-based algorithm. We do extensive experiments in natural images and remote sensing images with different magnifying factors and compare our method with three classical super-resolution methods. The subjective visual impression and quantitative evaluation indexes both show that our method can obtain higher-quality results.

Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion

With continuous developments in deep learning, image semantic segmentation technology has also undergone great advancements and been widely used in many fields with higher segmentation accuracy. This paper proposes an image semantic segmentation algorithm based on a deep neural network. Based on the Mask Scoring R-CNN, this algorithm uses a symmetrical feature pyramid network and adds a multiple-threshold architecture to improve the sample screening precision. We employ a probability model to optimize the mask branch of the model further to improve the algorithm accuracy for the segmentation of image edges. In addition, we adjust the loss function so that the experimental effect can be optimized. The experiments reveal that the algorithm improves the results.

Research on classification and identification of library based on artificial intelligence

With the popularization of open borrowing, it is urgent for major libraries to explore new collection classification and identification systems to assist or replace librarians in their daily book cataloguing work. The messy books can be marked according to invisible colors, which puts forward a new method of library classification. In the algorithm used to detect image edges, by looking for the traditional sensitivity measurement system, the best parameters are applied to the wrong book image edges, and the test results are verified to find the best parameter range. A two-dimensional algorithm is used to segment the information element matrix to reduce sound. The results show that the image edge test is effective and reduces the influence of noise on the image test. The self-adjustment control algorithm of a single neuron is used to control the robot orbit, which makes the robot not only react quickly, but also reduce a small part of the error in meeting the actual needs of the robot. The effect on the result is getting smaller and smaller.

Experimental Investigation of Anisotropic Diffusion Applied in Ghost Imaging Reconstruction

In iterative pseudo-inverse ghost imaging (IPGI), how much the noise interference item of the current iteration approximates the real noise greatly depends on the clarity of initial image. In order to improve IPGI, we propose a method that introduces anisotropic diffusion to construct a more accurate noise interference term, where anisotropic diffusion adapts to both the image and the noise, so that it balances the tradeoff between noise removal and preservation of image details. In our algorithm, the anisotropic diffusion equation is used to denoise the result of each iteration, then the denoised image is used to construct the noise interference term for the next iteration. Compared to IPGI, our method has better performance in visual effects and imaging quality, as the image edges and details are better preserved according to the experimental results.