Ultrasound Image Texture Feature Learning-Based Breast Cancer Benign and Malignant Classification

The use of ultrasound images to acquire breast cancer diagnosis information without invasion can reduce the physical and psychological pain of breast cancer patients and is of great significance for the diagnosis and treatment of breast cancer. There are some differences in the texture of breast cancer between benign and malignant cases. Therefore, this paper proposes an adaptive learning method based on ultrasonic image texture features to identify breast cancer. Specifically, firstly, we used dictionary learning and sparse representation to learn the ultrasonic image texture dictionary of benign and malignant cases, respectively, and then used the combination of the two dictionaries to represent the test image to obtain the texture distribution characteristics of the test image under the two dictionary representations, which called the sparse representation coefficient. Finally, these above features were filtered by sparse representation and sent to sparse representation classifier to establish benign and malignant classification model. 128 cases were randomly divided into training and testing sets according to 2: 1 for training and testing. The proposed method has achieved state-of-the-art results, with an accuracy of 0.9070 and the area under the receiver operating characteristic curve of 0.9459. The results demonstrate that the proposed method has the potential to be used in the clinical diagnosis of benign and malignant breast cancer.

A Histogram-Based Low-Complexity Approach for the Effective Detection of COVID-19 Disease from CT and X-ray Images

The global COVID-19 pandemic certainly has posed one of the more difficult challenges for researchers in the current century. The development of an automatic diagnostic tool, able to detect the disease in its early stage, could undoubtedly offer a great advantage to the battle against the pandemic. In this regard, most of the research efforts have been focused on the application of Deep Learning (DL) techniques to chest images, including traditional chest X-rays (CXRs) and Computed Tomography (CT) scans. Although these approaches have demonstrated their effectiveness in detecting the COVID-19 disease, they are of huge computational complexity and require large datasets for training. In addition, there may not exist a large amount of COVID-19 CXRs and CT scans available to researchers. To this end, in this paper, we propose an approach based on the evaluation of the histogram from a common class of images that is considered as the target. A suitable inter-histogram distance measures how this target histogram is far from the histogram evaluated on a test image: if this distance is greater than a threshold, the test image is labeled as anomaly, i.e., the scan belongs to a patient affected by COVID-19 disease. Extensive experimental results and comparisons with some benchmark state-of-the-art methods support the effectiveness of the developed approach, as well as demonstrate that, at least when the images of the considered datasets are homogeneous enough (i.e., a few outliers are present), it is not really needed to resort to complex-to-implement DL techniques, in order to attain an effective detection of the COVID-19 disease. Despite the simplicity of the proposed approach, all the considered metrics (i.e., accuracy, precision, recall, and F-measure) attain a value of 1.0 under the selected datasets, a result comparable to the corresponding state-of-the-art DNN approaches, but with a remarkable computational simplicity.

Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network

In this paper, we propose a novel method for plant leaves recognition by incorporating an unsupervised convolutional auto-encoder (CAE) and Siamese neural network in a unified framework by considering Siamese as an alternative to the conventional loss of CAE. Rather than the conventional exploitation of CAE and Siamese, in our case we have proposed to extend CAE for a novel supervised scenario by considering it as one-class learning classifier. For each class, CAE is trained to reconstruct its positive and negative examples and Siamese is trained to distinguish the similarity and the dissimilarity of the obtained examples. On the contrary and asymmetric to the related hierarchical classification schemes which require pre-knowledge on the dataset being recognized, we propose a hierarchical classification scheme that doesn’t require such a pre-knowledge and can be employed by non-experts automatically. We cluster the dataset to assemble similar classes together. A test image is first assigned to the nearest cluster, then matched to one class from the classes that fall under the determined cluster using our novel one-class learning classifier. The proposed method has been evaluated on the ImageCLEF2012 dataset. Experimental results have proved the superiority of our method compared to several state-of-the art methods.

DETECTING THE TEXTURE FOR MOBILE IMAGE BY USING PROPOSED TECHNIQUE

In this proposed search, a new technique was applied as an attempt to detect texture and the edges of a test image for mobile, lines drawn on a draft paper. Then was applied traditional spatial filters such as Sobel and Canny, comparison between them, and proposed method to detect the line edge and texture for the same image were applied. The results were that the detection method using the Canny filter showed more visual information and better accuracy than the Sobel spatial filter method, and when using the proposed technique, it gaves more information about the texture of the paper and more accurate results than the Canny filter, which was unable to detect the texture of the image.

Early visual processing relevant to the reduction of adaptation-induced perceptual bias

Visual perception is biased by the preceding visual environment. A well-known perceptual bias is the negative bias where a current percept is biased away from the preceding image (adaptor). The preceding adaptor induces augmentation of early visual evoked potential (the P1 enhancement) of the following test image; the adaptor may invoke certain visual processing for the subsequent test image. However, the visual mechanism underlying P1 enhancement remains unclear. The present study assessed what the P1 alteration reflects in relation to the occurrence of the negative bias. In terms of inter-individual differences, we report that the P1 enhancement of the Necker lattice significantly correlated with the reduction of the reverse-bias effect. Further analyses revealed that the P1 enhancement was insusceptible to neural adaptation to the adaptor at the level of perceptual configuration. The present study suggests that prolonged exposure to a visual image induces modulatory visual processing for the subsequent image (reflected in the P1 enhancement), which is relevant to counteraction of the negative bias.

METHOD FOR STEGANOGRAPHIC HIDE OF INFORMATION BASED ON CONTINUOUS WAVELET TRANSFORM

This article discusses continuous wavelet transform as a method of steganographic embedding of confidential information into an image. The main purpose of steganography is to hide information so that the possibility of data detection is minimized. This is done by hiding the message inside the container so that outsiders are not aware of the secret’s existence. Thus, the main principle of steganography is the principle of invisibility, which is also the basis of security when using these systems to transfer information. Steganography methods are divided into two large groups: spatial and frequency. The former visually degrade the image quality by directly changing the components (pixels). The latter interact with frequency characteristics, which has the best effect on the quality of the converted image. At this point in time, one of the most common frequency methods (discrete-cosine transform) is increasingly being replaced by a wavelet transform. This method of embedding confidential information is visually less noticeable to human vision, relative to those existing at a given time.The paper presents brief theoretical information on the wavelet transform, gives the characteristics of the Haar transform, presents images demonstrating the principle of the wavelet transform. The developed algorithm for steganography based on the wavelet transform is shown. The algorithm was implemented in the Matlab environment, as well as the analysis of the results obtained using the example of a test image. Conclusions, advantages of this method, as well as recommendations for further research in this area are given.

Object Detection Combining CNN and Adaptive Color Prior Features

When compared with the traditional manual design method, the convolutional neural network has the advantages of strong expressive ability and it is insensitive to scale, light, and deformation, so it has become the mainstream method in the object detection field. In order to further improve the accuracy of existing object detection methods based on convolutional neural networks, this paper draws on the characteristics of the attention mechanism to model color priors. Firstly, it proposes a cognitive-driven color prior model to obtain the color prior features for the known types of target samples and the overall scene, respectively. Subsequently, the acquired color prior features and test image color features are adaptively weighted and competed to obtain prior-based saliency images. Finally, the obtained saliency images are treated as features maps and they are further fused with those extracted by the convolutional neural network to complete the subsequent object detection task. The proposed algorithm does not need training parameters, has strong generalization ability, and it is directly fused with convolutional neural network features at the feature extraction stage, thus has strong versatility. Experiments on the VOC2007 and VOC2012 benchmark data sets show that the utilization of cognitive-drive color priors can further improve the performance of existing object detection algorithms.

An Improved Algorithm for Detection and Pose Estimation of Texture-Less Objects

This paper introduces an improved algorithm for texture-less object detection and pose estimation in industrial scenes. In the template training stage, a multi-scale template training method is proposed to improve the sensitivity of LineMOD to template depth. When this method performs template matching, the test image is first divided into several regions, and then training templates with similar depth are selected according to the depth of each test image region. In this way, without traversing all the templates, the depth of the template used by the algorithm during template matching is kept close to the depth of the target object, which improves the speed of the algorithm while ensuring that the accuracy of recognition will not decrease. In addition, this paper also proposes a method called coarse positioning of objects. The method avoids a lot of useless matching operations, and further improves the speed of the algorithm. The experimental results show that the improved LineMOD algorithm in this paper can effectively solve the algorithm’s template depth sensitivity problem.