基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

基于多尺度结构特征的快速异源图像匹配

针对异源图像提出一种基于多尺度密集结构特征的快速匹配算法。算法首先利用Gabor滤波器逐像素提取图像中的结构响应,再根据主方向响应对多尺度结构特征融合,然后使用快速傅里叶变换在频域计算各特征分量图像之间的卷积,最后将卷积生成的系数矩阵求和计算出图像之间的相似性并选择相似性最大位置作为匹配结果输出。本文算法能有效适应异源图像间的非线性灰度变化和噪声干扰问题。测试使用可见光、红外、雷达图像组成的异源图像数据集对本文算法和现有算法进行测试比较,结果表明:本文算法的平均误匹配率最低,并且计算速度有明显优势。     

A novel multi-focus image fusion method based on distributed compressed sensing

Multi-focus image fusion aims to produce an all-in-focus image by merging multiple partially focused images of the same scene. The main work is identifying the focused region and then composing all the focused regions. In this paper, a novel efficient multi-focus image fusion method based on distributed compressed sensing (DCS) is proposed. Firstly, the low-frequency and high-frequency images are obtained by comparing the variance of the source images, which are further utilized to get the low-frequency and high-frequency dictionaries. Secondly, DCS using joint sparsity model-1 (JSM-1) is applied to reconstruct the precise high-frequency images. Thirdly, the decision map is obtained based on all the high-frequency images and then improved by the morphological processing. Finally, the focused pixels are chosen from the source images through the decision map. Experimental results indicate that the proposed DCS-based method can be competitive with or even outperform some state-of-the-art methods in terms of both visual and quantitative metric evaluations.     

Copy-move forgery detection of duplicated objects using accurate PCET moments and morphological operators

This paper presents a new method for copy-move forgery detection of duplicated objects. A bounding rectangle is drawn around the detected object to form a sub-image. Morphological operator is used to remove the unnecessary small objects. Highly accurate polar complex exponential transform moments are used as features for the detected objects. Euclidian distance and correlation coefficient between the feature vectors are calculated and used for searching the similar objects. A set of 20 forged images with duplicated objects is carefully selected from previously published works. Additional 80 non-forged images are edited by the authors and forged by duplicating different kinds of objects. Numerical simulation is performed where the results show that the proposed method successfully detect different kinds of duplicated objects. The proposed method is much faster than the previously existing methods. Also, it exhibits high robustness to various attacks such as additive white Gaussian noise, JPEG compression, rotation, and scaling.     

An Integrated Flexible All-Nanowire Infrared Sensing System with Record Photosensitivity

Infrared (IR) photodetectors are a key optoelectronic device and have thus attracted considerable research attention in recent years. Photosensitivity is an increasingly important device performance parameter for nanoscale photodetectors and image sensors, as it determines the ultimate imaging quality and contrast. However, photosensitivities of state-of-the-art low-dimensional nanostructure-based IR detectors are considerably low, limiting their practical applications. Herein, a biomimetic IR detection amplification (IRDA) system that boosts photosensitivity by several orders of magnitude by introducting nanowire field effect transistors (FETs), resulting in a peak photosensitivity of 7.6 × 10⁴ under an illumination of 1342 nm, is presented. Consequently, high-contrast imaging of IR light is obtained on the flexible IRDA arrays. The image information can be then trained and recognized by an artificial neural network for higher image-recognition efficiency. This work provides a new perspective for developing high-performance IR imaging systems, and is expected to undoubtedly enlighten future work on artificial intelligence and biorobotic systems.     

Why stop after 20 minutes? Breaks and target prevalence in a 60-minute X-ray baggage screening task

Current EU regulation restricts continuously reviewing X-ray images of passenger baggage to 20-min duration as a precautionary measure to prevent performance decrements in airport security officers (screeners). However, this 20-min limit is not based on clear empirical evidence on how well screeners can sustain their performance over time. Our study tested screeners in a 60-min simulated X-ray cabin baggage screening task. One group took 10-min breaks after 20 min of screening; the other group worked without breaks. We found no decrease in performance over 60 min in either group. Breaks did not affect performance, but they did reduce the amount of subjective distress. By varying target prevalence, we found that d_a with a slope of about 0.6 is a more valid measure of detection performance than d'. Target prevalence caused a criterion shift. Our results provide a basis for conducting field studies of prolonged screening durations, and open the discussion on whether more flexible break policies and work schedules should be considered.     

基于信息熵与形态学的鸟鸣数据处理

为了探索一种减少训练量并提高精度,且适应于卷积神经网络的预处理方法,以识别鸟鸣为例,基于信息熵以及形态学在图像处理上的应用,根据鸟鸣的间隔性特点,提出新的处理方案。利用形态学将音频片段归类为有效和噪声信号两类;使用加权的方法利用信息熵预测有效数据的分布。仿真结果表明,形态学使数据量减少且信息熵处理使单个数据稀疏化并起到滤波作用,在保持精度甚至精度提高的情况下缩短了训练时间,为卷积神经网络的数据预处理的简化提供了方向。     

基于微流控的人卵母细胞特性检测

人的卵母细胞特性的研究对于临床医学具有重要意义,可以通过卵母细胞的大小对其活性进行研究。采用微流控平台与MATLAB算法相结合的方法,利用微流控器件的沟道对卵母细胞进行挤压,由于卵母细胞的活性不同对于挤压的反应也不同,活性越好的卵母细胞通过沟道时变形性越好,经检测卵母细胞有很好的活性;拍摄卵母细胞发生形变与卵母细胞通过沟道的视频,利用MATLAB程序进行图像处理得到卵母细胞的大小,测得卵母细胞的直径约为170μm。这种方法有别于传统方法,在一定程度上使用了算法识别,提高了卵母细胞分析统计的准确度,提升了工作效率。由于人的卵母细胞比较珍贵,只进行了初期实验研究,证明此方法确实可行。     

多线激光V型焊缝图像特征提取与轨迹识别

为了减少焊缝识别中传感器安装位置带来的前置误差，提高识别精度，设计了一款多线激光传感器，对多线激光在V型焊缝上的图像进行处理得到焊缝轨迹。提出一种基于动态不规则感兴趣区域的图像分割方法，将多条激光分割后并行处理。单条激光线图像预处理后以像素行灰度值之和的极大值确定激光条纹所在行，对激光条纹分段拟合后求交点，得到坡口边缘与焊缝位置的特征点，并将焊缝位置特征点拟合得到焊缝轨迹。根据所提出的算法编写了焊缝轨迹识别程序，并进行实验，结果表明，所提出的算法识别焊缝走向误差在0.5°之内，符合焊缝跟踪的要求。     

Application of fuzzy image restoration in criminal investigation

The advancement of science and technology has a positive effect on the development of law disciplines. The development of algorithms and artificial intelligence also has a certain impact on judicial practice. Image restoration is a significant technique in image processing. It aims to objectively restore the content or quality of the original image from the degraded image. Image degradation is always generated in image transmission, such as distortion, blur. In modern video surveillance system, image restoration is significant for criminal investigation. However, image restoration based on conventional filter algorithms cannot achieve satisfactory performance. Thus, we first introduce the image restoration algorithms based on different degradation model. Then, we propose some applications of fuzzy image restoration in criminal investigation. We conduct experiments on both degraded images and videos and experimental results have shown the effectiveness of fuzzy image restoration applying to the criminal investigation.