Image classification with a chirp-encoded joint transform correlator

We describe a method of performing image classification with a chirp-encoded joint transform correlator. In the proposed system the reference images and the input image that is to be classified are placed in different input planes of the joint transform correlator. As a result, different output planes of the correlator are associated with each reference image. The input image is classified on the basis of the intensity and the spatial position of the correlation peak. The reference images and the input image can be positioned in one input plane with glass blocks of different thicknesses placed on each reference image. This produces the same effect as having the reference images and the input image in different planes. Analytical expressions, computer simulations, and optical experiments are presented to investigate the performance of the chirp-encoded joint transform correlator for image classification.     

CNN-Based Forensic Method on Contrast Enhancement with JPEG Post-Processing

As one of the most popular digital image manipulations, contrast enhancement (CE) is frequently applied to improve the visual quality of the forged images and conceal traces of forgery, therefore it can provide evidence of tampering when verifying the authenticity of digital images. Contrast enhancement forensics techniques have always drawn significant attention for image forensics community, although most approaches have obtained effective detection results, existing CE forensic methods exhibit poor performance when detecting enhanced images stored in the JPEG format. The detection of forgery on contrast adjustments in the presence of JPEG post processing is still a challenging task. In this paper, we propose a new CE forensic method based on convolutional neural network (CNN), which is robust to JPEG compression. The proposed network relies on a Xception-based CNN with two preprocessing strategies. Firstly,unlike the conventional CNNs which accepts the original image as its input, we feed the CNN with the gray-level co-occurrence matrix (GLCM) of image which contains CE fingerprints, then the constrained convolutional layer is used to extract high-frequency details in GLCMs under JPEG compression, finally the output of the constrained convolutional layer becomes the input of Xception to extract multiple features for further classification. Experimental results show that the proposed detector achieves the best performance for CE forensics under JPEG post-processing compared with the existing methods.     

Cascaded networks for the embryo classification on microscopic images using the residual external-attention

Embryo assessment and selection are usually based on the visual morphological analysis by expert embryologists. Although the embryologist assessment has been routinely used in clinical practice, it is highly dependent on the embryologist's experience and is very time-consuming. Therefore, objective and efficient methods for automated embryo evaluation are in high demand. We proposed a framework of cascaded networks to hierarchically extract and integrate the microscopic image features for embryo classification. The cascaded networks consisted of a coarse network and a refined network. The coarse network produced a classification activation mapping (CAM) with the highest classification probability, which indicated the most discriminative regions of embryo classification. The refined network extracted and integrated the image features again by using both the CAMs and the corresponding original images. In addition, the residual external-attention block (ResEA) was used in the refined network to better capture long-range dependencies. Our cascaded networks were trained on a dataset of 7728 microscopic images of day 3 embryos from 1800 couples and evaluated on an independent testing dataset of 734 microscopic images. The accuracy, sensitivity, specificity, precision, and F1-score were employed to evaluate the performance of our cascaded networks. Compared with the coarse network and the refined network, respectively, the cascaded networks without the ResEA improved the classification results of embryos. The ResEA block helped the cascaded networks to further improve all five metrics for better embryo classification. Our proposed cascaded networks also achieved better classification results than a junior embryologist did. The cascaded networks hierarchically make full use of image features for more effective learning, and the ResEA further improves the performance of embryo classification.     

Efficient image compression techniques for compressing multimodal medical images using neural network radial basis function approach

Image compression technique is used to reduce the number of bits required in representing image, which helps to reduce the storage space and transmission cost. Image compression techniques are widely used in many applications especially, medical field. Large amount of medical image sequences are available in various hospitals and medical organizations. Large images can be compressed into smaller size images, so that the memory occupation of the image is considerably reduced. Image compression techniques are used to reduce the number of pixels in the input image, which is also used to reduce the broadcast and transmission cost in efficient form. This is capable by compressing different types of medical images giving better compression ratio (CR), low mean square error (MSE), bits per pixel (BPP), high peak signal to noise ratio (PSNR), input image memory size and size of the compressed image, minimum memory requirement and computational time. The pixels and the other contents of the images are less variant during the compression process. This work outlines the different compression methods such as Huffman, fractal, neural network back propagation (NNBP) and neural network radial basis function (NNRBF) applied to medical images such as MR and CT images. Experimental results show that the NNRBF technique achieves a higher CR, BPP and PSNR, with less MSE on CT and MR images when compared with Huffman, fractal and NNBP techniques.     

图片卫士:一个自动成人图像识别系统

设计并实现了一个自动识别成人图像识别系统“图片卫士”。图片卫士采用3层识别框架,利用肤色、纹理、图像视觉特征分层逐级识别成人图像。为了可靠地检测到图像中的肤色区域,提出了一种新的自适应统计肤色模型。在肤色检测基础上,通过皮肤纹理验证过程,图像中的人体皮肤区域被准确地分割出来。基于图像中皮肤区域,提取9个经验特征来表示图像内容,并采用AdaBoost算法构造一个总体分类器进行图像分类,识别正常图像和成人图像。在算法评估中,建立了一个78205幅图像的测试集,其中59885幅为正常图像,18320幅为成人图像。图片卫士显示了良好的系统性能,具有成人图像88．5％的识别率,正常图像92．5％的识别率。在PentiumⅣ1．5GHz的个人计算机上,图片卫士的平均处理速度为正常图像每秒5．6幅和成人图像每秒1．9幅。图片卫士可以应用在个人计算机或网络传输中,实时监控和过滤成人图像,还可以为网络安全等应用提供技术支持。     

Image identification system based on an optical broadcast neural network processor

We describe the implementation of a vision system based on a hardware neural processor. The architecture of the neural network processor has been designed to exploit the computational characteristics of electronics and the communication characteristics of optics in an optimal manner, thus it is based on an optical broadcast of input signals to a dense array of processing elements. The vision system has been built by use of a prototype implementation of a neural network processor with discrete optic and optoelectronic devices. It has been adapted to work as a Hamming classifier of the images taken with a 128 x 128 complementary metal-oxide semiconductor image sensor. Its results, performance characteristics of the image classification system, and an analysis of its scalability in size and speed, with the improvement of the optoelectronic neural processor, are presented.     

Performance analysis of neural networks for classification of medical images with wavelets as a feature extractor

In this article, we analyze the performance of artificial neural network, in classification of medical images using wavelets as feature extractor. This work classifies the mammographic image, MRI images, CT images, and ultrasound images as either normal or abnormal. We have tested the proposed approach using 50 mammogram images (13 normal and 37 abnormal), 24 MRI brain images (9 normal and 15 abnormal), 33 CT images (11 normal and 22 abnormal), and 20 ultrasound images (6 normal and 14 abnormal). Four kind of neural network models such as BPN (Back Propagation Network), Hopfield, RBF (Radial Basis Function), and PNN (Probabilistic neural network) were chosen for study. To improve diagnostic accuracy, the feature extracted using wavelets such as Harr, Daubechies (db2, db4, and db8), Biorthogonal and Coiflet wavelets are given as input to the neural network models. Good classification percentage of 96% was achieved using the RBF when Daubechies (db4) wavelet based feature extraction was used. We observed that the classification rate is almost high under the RBF neural network for all the dataset considered. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 33–40, 2015     

Digital Forensics for Recoloring via Convolutional Neural Network

As a common medium in our daily life, images are important for most people to gather information. There are also people who edit or even tamper images to deliberately deliver false information under different purposes. Thus, in digital forensics, it is necessary to understand the manipulating history of images. That requires to verify all possible manipulations applied to images. Among all the image editing manipulations, recoloring is widely used to adjust or repaint the colors in images. The color information is an important visual information that image can deliver. Thus, it is necessary to guarantee the correctness of color in digital forensics. On the other hand, many image retouching or editing applications or software are equipped with recoloring function. This enables ordinary people without expertise of image processing to apply recoloring for images. Hence, in order to secure the color information of images, in this paper, a recoloring detection method is proposed. The method is based on convolutional neural network which is quite popular in recent years. Unlike the traditional linear classifier, the proposed method can be employed for binary classification as well as multiple labels classification. The classification performance of different structure for the proposed architecture is also investigated in this paper.     

应用Deeplab V3+网络实现小儿髋关节超声图像识别

利用Graf法进行发育性髋关节发育不良(Developmental Dysplasia of the Hip, DDH)诊断时主要依靠骨-软骨交界面、股骨头、滑膜皱襞、关节囊及软骨膜、盂唇、软骨顶、骨性顶这7个解剖结构进行解剖验证,而初级医生对上述结构识别困难,因此文章提出了一种基于DeeplabV3+的网络模型用于7个结构的分割识别。首先对纳入的106例图像进行手动标记和预处理,之后将其分别输入DeeplabV3+和U-Net两种网络模型中,最终对其预测图表现和分割性能进行比较。与目前DDH图像分割中常用且表现优越的U-Net网络相比,DeeplabV3+网络的预测图包含的结构较多,边界分割也较清晰,其图像分割评价指标如相似性系数、豪斯多夫距离和平均豪斯多夫距离平均值的表现也优于U-Net网络。文章利用DeeplabV3+网络实现了DDH超声图像的7个结构分割,对临床医生进行后续图像的角度测量和分型诊断具有重要意义。     

Improved classification robustness for noisy cell images represented as principal-component projections in a hybrid recognition system

Different types of cells are recognized from their noisy images by use of a hybrid recognition system that consists of a learning principal-component analyzer and an image-classifier network. The inputs to the feed-forward backpropagation classifier are the first 15 principal components of the 10 x 10 pixel image to be classified. The classifier was trained with clear images of cells in metaphase, unburst cells, and other erroneous patterns. Experimental results show that the recognition system is robust to image scaling and rotation, as well as to image noise. Cell recognition is demonstrated for images that are corrupted with additive Gaussian noise, impulse noise, and quantization errors. We compare the performance of the hybrid recognition system with that of a conventional three-layer feed-forward backpropagation network that uses the raw image directly as input.     

基于OCT成像的淡水无核珍珠内部缺陷自动检测方法

光学相干层析技术(OCT)作为一种高分辨率的无损光学检测手段,已被用于珍珠的内部质量检测。针对淡水无核珍珠质层内部缺陷检测的需求,提出一种通过光学相干层析图像实现淡水无核珍珠内部缺陷自动检测的方法。根据珠层灰度变化的特点,识别图像中缺陷区域的梯度特征和缺陷位置变化特征,并利用缺陷特征建立反向传播神经网络模型。实验中采集了内部无缺陷和内部有多种类型缺陷淡水无核珍珠的光学相干层析图像各20幅,对图像进行预处理并提取特征,利用K-means算法检测样本类型与所提取特征的匹配度,用特征与类型相匹配的样本特征训练反向传播神经网络模型,使用反向传播网络模型对淡水无核珍珠内部缺陷层进行分类识别。实验结果表明该方法提取特征的匹配度为92.5%,分类准确率达到100%,验证了该方法的可行性和有效性,提出的方法能够作为淡水无核珍珠内部缺陷识别和自动分类的有效手段。     

Effect of image resolution on intensity based scene illumination classification using neural network

In this paper, a framework for testing scene illumination classification with different image resolutions is proposed. The testing aims to provide the researchers with valuable information about the effect of image resolution on scene illumination classification using a neural network. The experiment is done by extracting three types of features from the images. These three types consist of statistical features, physic based features and histogram based features. It has been demonstrated that scene illumination classification can be affected by changing the image resolution. Despite the popular belief that high resolution images lead to better results, scene illumination classification by the proposed method performed best using low resolution images. At the second part of discussion, the reason behind this phenomenon is mathematically analysed and explained.     

应用ICA滤波器技术提取图像纹理特征

针对纹理图像分类问题,本文提出了一种应用ICA滤波器技术提取图像纹理特征的方法.该方法首先从训练图像集中随机抽取图像块作为观测信号,应用ICA技术,提取滤波器组.然后根据训练样本图像对滤波器组的响应值来评估和选择滤波器组,达到降维的目的.最后利用滤波器组对测试图像进行滤波,得到该图像的滤波响应结果,从该响应结果中得到最大响应滤波器编号,提取其直方图作为图像的全局特征和局部特征.对Brodatz纹理图像集中108个纹理类别进行了分类实验,结果表明,与MPEG-7纹理描述子相比,该图像特征对纹理图像具有更好的分类效果.     

基于卷积神经网络与门控循环单元的气液两相流流型识别方法

提出了一种基于卷积神经网络(CNN)与门控循环单元(GRU)的垂直管道气液两相流流型识别方法。该方法基于电阻层析成像(ERT)系统的重建图像,对其填充处理后进行离散余弦变换(DCT),求取最大、最小 DCT 系数的差值,选取一定帧数长度数据作为网络输入,对流型进行识别。分析了输入序列长度对CNN-GRU、CNN 及 GRU 网络分类准确的影响,确定了最佳输入向量维度分别为 60、65 及 50,使用实验数据对3种网络进行训练、测试,结果表明,CNN-GRU网络分类准确率最高,平均流型识别准确率可达 99.40%。     

A 360-Degree Panoramic Image Inpainting Network Using a Cube Map

Inpainting has been continuously studied in the field of computer vision. As artificial intelligence technology developed, deep learning technology was introduced in inpainting research, helping to improve performance. Currently, the input target of an inpainting algorithm using deep learning has been studied from a single image to a video. However, deep learning-based inpainting technology for panoramic images has not been actively studied. We propose a 360-degree panoramic image inpainting method using generative adversarial networks (GANs). The proposed network inputs a 360-degree equirectangular format panoramic image converts it into a cube map format, which has relatively little distortion and uses it as a training network. Since the cube map format is used, the correlation of the six sides of the cube map should be considered. Therefore, all faces of the cube map are used as input for the whole discriminative network, and each face of the cube map is used as input for the slice discriminative network to determine the authenticity of the generated image. The proposed network performed qualitatively better than existing single-image inpainting algorithms and baseline algorithms.     

Neural network classifier and multiple hypothesis image segmentation for dietary assessment using calorie calculator

Nowadays, dietary assessment becomes the emerging system for evaluating the person’s food intake. In this paper, the multiple hypothesis image segmentation and feed-forward neural network classifier are proposed for dietary assessment to enhance the performance. Initially, the segmentation is applied to input image which is used to determine the regions where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the significant feature of food items is extracted by the global feature and local feature extraction method. After the features are obtained, the classification is performed for each segmented region using feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food area volume and (ii) calorie and nutrition measure based on mass value. The outcome of the proposed method attains 96% of accuracy value which provides the better classification performance.     

神经网络在二维图像识别中的应用

本文提出了一种基于神经网络的二维图像识别技术。选取一组机械零件的二维图像,对每张图像进行放缩和旋转变换,并分析、提取对应图像的nmi特征和7个不变矩特征作为BP网络的输入样本,图像的二进制编号为输出样本构建BP神经网络。并对网络进行抗干扰训练,使网络对理想输入及带噪声的输入均有较好的识别率。实验证明该网络具有一定的工程实用性。     

Classification and Research of Skin Lesions Based on Machine Learning

Classification of skin lesions is a complex identification challenge. Due to the wide variety of skin lesions, doctors need to spend a lot of time and effort to judge the lesion image which zoomed through the dermatoscopy. The diagnosis which the algorithm of identifying pathological images assists doctors gets more and more attention. With the development of deep learning, the field of image recognition has made longterm progress. The effect of recognizing images through convolutional neural network models is better than traditional image recognition technology. In this work, we try to classify seven kinds of lesion images by various models and methods of deep learning, common models of convolutional neural network in the field of image classification include ResNet, DenseNet and SENet, etc. We use a fine-tuning model with a multi-layer perceptron, by training the skin lesion model, in the validation set and test set we use data expansion based on multiple cropping, and use five models’ ensemble as the final results. The experimental results show that the program has good results in improving the sensitivity of skin lesion diagnosis.     

Quantitative measurement of texture orientation in biomedical images using an artificial neural network

Texture orientation is one of the most important attributes used in biomedical and clinical image interpretation. It provides critical clues of continuity and connectivity useful in relating adjacent image areas. We report a novel approach in which image data are convolved with directional convolution masks and the results are used as input to an artificial neural network for classification of image areas into a number of discrete texture orientation classes. © 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 351–355, 1998     

基于PCNN的图像融合新方法

本文提出了一种基于PCNN的新型图像融合算法.首先,对待融合的两幅图像进行平稳小波分解得到两组多尺度图像;接着,取其中任意一组作为主PCNN的输入、另一组相应的图像作为从PCNN的输入,在每次迭代时,经并行PCNN点火后,得到一系列多尺度融合图像;然后,对它们进行平稳小波反变换得到每次迭代的融合结果;最后,计算每次迭代结果的信息熵,取信息熵值最大的融合图像作为最终结果.大量的实验以及与其它融合算法的比较分析,表明了本文算法的有效性和优越性.