动物的逃生手段——自割

动物保护自己的方法有许多种,但最有趣的是自割。就是当动物遇到要吃它的强敌时,能毫不犹豫地舍去自己身体的一部分,然后逃走。壁虎和蜥蜴遇到强敌侵害时,能把尾巴断掉,每条壁虎和蜥蜴尾巴断的部位都是相同的。断下来的这段尾巴有神经,能独立地来回摆动。

语辞辑释

笔者曾与先师郭在贻教授及师兄张涌泉合作完成《敦煌变文释词》等①,此文再辑数条俗语考释之,所引材料皆直接录自原卷缩微胶卷(若先已有录本则皆重新核实),故文内径称原编号及篇题。

居功贪赏者鉴

春秋五霸之一的晋文公(公子重耳),在其作国君之前,曾因晋国騼姬之难而出亡他国,过了长达十九年的流亡生活。由于随从人员的辅佐,并得秦穆之援,终于归国为君。出亡期间,虽也有暂享安逸之时,但却也“险阻难艰,备尝之矣”。(《左传·僖公二十八年》)晋文公深知自己的国君之位来之不易,故卽位不久,卽重赏那些跟随自己过流亡生活并为自己的事业出谋尽力之人。介之推是晋文公的一位从亡者,当年在困乏冻馁之时,曾“自割其股以食文公”。(《庄子·盗跖》)对文公可谓忠矣,功劳可谓大矣。可是,当晋文公赏从亡者的时候,赏不及介之推,而介之推本人也不居功索求。介之推认为,晋文公所以能够归国为君,并不只是几个从亡者之功。有些人因从亡并为晋文公取得国君地位出过力,就自居功臣,贪求高官厚禄的封赏,那是“贪天之功以为己力”的罪人,耻于与之共事。于是,退隐绵上,不仕而死。(见《左传·僖公二十四年》)

Clustering-driven watershed adaptive segmentation of bubble image

In order to extract froth morphological feature,a bubble image adaptive segmentation method was proposed.Considering the image's low contrast and weak froth edges,froth image was coarsely segmented by using fuzzy c means(FCM) algorithm. Through the attributes of size and shape pattern spectrum,the optimal morphological structuring element was determined.According to the optimal parameters,some image noises were removed with an improved area opening and closing by reconstruction operation,which consist of image regional markers,and the bubbles were finely separated from each other by watershed transform.The experimental results show that the structural element can be determined adaptively by shape and size pattern spectrum,and the froth image is segmented accurately.Compared with other froth image segmentation method,the proposed method achieves much high accuracy,based on which,the bubble size and shape features are extracted effectively.

Automatic segmentation of Colon Cancer Cells Based on Active Contour Method： A New Approach

Automatic interpretation of the images of colon cell biopsies requires automatic segmentation of these cells in the image obtained. The active contour method for image segmentation is a well known method for automatic detection of the cell contour. However, the application of this method on colon cell images was not effective. In this paper, the authors have proposed a new technique to reduce the analysis time needed to detect cells in a given image. This technique is based on the active contour method but now using a progressive division of the dimensions of the image to achieve convergence. The model proposed succeeded in detecting cells whose boundaries are not necessarily defined by a gradient. The initial curve can be anywhere in the image, and interior contours can be automatically detected. The developed algorithm was successfully applied on textured multispectral images of three types of cells, including benign hyperplasia （BH）, intraepithelial neoplasia （IN）, and carcinoma （Ca） cells.

ADAPTIVE RIVER SEGMENTATION IN SAR IMAGES

There is difficulty for distinguishing of river and shadow in Synthetic Aperture Radar (SAR) images. A method of river segmentation in SAR images based on wavelet energy and gradient is proposed in this paper. It mainly includes two algorithms: coarse segmentation and refined segmen- tation. Firstly, The river regions are coarsely segmented by the wavelet energy feature,and then refined segmented accurately by the gradient threshold which is got adaptively. The experimental results show the validity of the method, which provides a good foundation for targets detection above the river.

A MICRO-IMAGE FUSION ALGORITHM BASED ON REGION GROWING

Due to the limitation of Depth Of Field (DOF) of microscope, the regions which are not within the DOF will be blurring after imaging. Thus for micro-image fusion, the most important step is to identify the blurring regions within each micro-image, so as to remove their undesirable impacts on the fused image. In this paper, a fusion algorithm based on a novel region growing method is proposed for micro-image fusion. The local sharpness of micro-image is judged block by block, then blocks whose sharpness is lower than an adaptive threshold are used as seeds, and the sharpness of neighbors of each seed are evaluated again during the region growing until the blurring regions are identified completely. With the decreasing in block size, the obtained region segmentation becomes more and more accurate. Finally, the micro-images are fused with pixel-wise fusion rules. The experimental results show that the proposed algorithm benefits from the novel region segmentation and it is able to obtain fused micro-image with higher sharpness compared with some popular image fusion method.

Adaptive foreground and shadow segmentation using hidden conditional random fields

Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).

AN AUTOMATIC SEGMENTATION METHOD FOR MOVING OBJECTS BASED ON THE SPATIAL-TEMPORAL INFORMATION OF VIDEO

The new MPEG-4 video coding standard enables content-based functions. In order to support the new standard, frames should be decomposed into Video Object Planes （VOP）, each VOP representing a moving object. This paper proposes an image segmentation method to separate moving objects from image sequences. The proposed method utilizes the spatial-temporal information. Spatial segmentation is applied to divide each image into connected areas and to find pre~：ise object boundaries of moving objects. To locate moving objects in image sequences, two consecutive image frames in the temporal direction are examined and a hypothesis testing is performed with Neyman-Pearson criterion. Spatial segmentation produces a spatial segmentation mask, and temporal segmentation yields a change detection mask that indicates moving objects and the background. Then spatial-temporal merging can be used to get the final results. This method has been tested on several images. Experimental results show that this segmentation method is efficient.

Structured-light Image Compression Based on Fractal Theory

The method of fractal image compression is introduced which is applied to compress the line structured light image. Based on the self similarity of the structured light image, we attain satisfactory compression ratio and higher peak signal to noise ratio (PSNR). The experimental results indicate that this method can achieve high performance.

Automatic cell object extraction of red tide algae in microscopic images

Extracting the cell objects of red tide algae is the most important step in the construction of an automatic microscopic image recognition system for harmful algal blooms.This paper describes a set of composite methods for the automatic segmentation of cells of red tide algae from microscopic images.Depending on the existence of setae,we classify the common marine red tide algae into non-setae algae species and Chaetoceros,and design segmentation strategies for these two categories according to their morphological characteristics.In view of the varied forms and fuzzy edges of non-setae algae,we propose a new multi-scale detection algorithm for algal cell regions based on border-correlation,and further combine this with morphological operations and an improved GrabCut algorithm to segment single-cell and multicell objects.In this process,similarity detection is introduced to eliminate the pseudo cellular regions.For Chaetoceros,owing to the weak grayscale information of their setae and the low contrast between the setae and background,we propose a cell extraction method based on a gray surface orientation angle model.This method constructs a gray surface vector model,and executes the gray mapping of the orientation angles.The obtained gray values are then reconstructed and linearly stretched.Finally,appropriate morphological processing is conducted to preserve the orientation information and tiny features of the setae.Experimental results demonstrate that the proposed methods can effectively remove noise and accurately extract both categories of algae cell objects possessing a complete shape,regular contour,and clear edge.Compared with other advanced segmentation techniques,our methods are more robust when considering images with different appearances and achieve more satisfactory segmentation effects.

Semantic segmentation method of road scene based on Deeplabv3+ and attention mechanism

In the study of automatic driving,understanding the road scene is a key to improve driving safety.The semantic segmentation method could divide the image into different areas associated with semantic categories in accordance with the pixel level,so as to help vehicles to perceive and obtain the surrounding road environment information,which would improve driving safety.Deeplabv3+is the current popular semantic segmentation model.There are phenomena that small targets are missed and similar objects are easily misjudged during its semantic segmentation tasks,which leads to rough segmentation boundary and reduces semantic accuracy.This study focuses on the issue,based on the Deeplabv3+network structure and combined with the attention mechanism,to increase the weight of the segmentation area,and then proposes an improved Deeplabv3+fusion attention mechanism for road scene semantic segmentation method.First,a group of parallel position attention module and channel attention module are introduced on the Deeplabv3+encoding end to capture more spatial context information and high-level semantic information.Then,an attention mechanism is introduced to restore the spatial detail information,and the data shall be normalized in order to accelerate the convergence speed of the model at the decoding end.The effects of model segmentation with different attention-introducing mechanisms are compared and tested on CamVid and Cityscapes datasets.The experimental results show that the mean Intersection over Unons of the improved model segmentation accuracies on the two datasets are boosted by 6.88%and 2.58%,respectively,which is better than using Deeplabv3+.This method does not significantly increase the amount of network calculation and complexity,and has a good balance of speed and accuracy.

Correlation analysis-based image segmentation approach for automatic agriculture vehicle

It is important to segment image correctly to extract guidance information for automatic agriculture vehicle. If we can make the computer know where the crops are, we can extract the guidance line easily. Images were divided into some rec-tangle small windows, then a pair of 1-D arrays was constructed in each small windows. The correlation coefficients of every small window constructed the features to segment images. The results showed that correlation analysis is a potential approach for processing complex farmland for guidance system, and more correlation analysis methods must be researched.

Random Walk Based Method for Automatic Segmentation of Intravascular Ultrasound Images

Intravascular ultrasound( IVUS) is an important imaging technique that is used to study vascular wall architecture for diagnosis and assessment of the vascular diseases. Segmentation of lumen and media-adventitia boundaries from IVUS images is a basic and necessary step for quantitative assessment of the vascular walls.Due to ultrasound speckles, artifacts and individual differences,automated segmentation of IVUS images represents a challenging task. In this paper,a random walk based method is proposed for fully automated segmentation of IVUS images. Robust and accurate determination of the seed points for different regions is the key to successful use of the random walk algorithm in segmentation of IVUS images and is the focus of the present work. Performance of the proposed algorithm was evaluated over an image database with 900 IVUS image frames of nine patient cases. The preliminary experimental results show the potential of the proposed IVUS image segmentation approach.

Recognition algorithm for turn light of front vehicle

Intelligent vehicle needs the turn light information of front vehicles to make decisions in autonomous navigation. A recognition algorithm was designed to get information of turn light. Approximated center segmentation method was designed to divide the front vehicle image into two parts by using geometry information. The number of remained pixels of vehicle image which was filtered by the morphologic feaatres was got by adaptive threshold method, and it was applied to recognizing the lights flashing. The experimental results show that the algorithm can not only distinguish the two turn lights of vehicle but also recognize the information of them. The algorithm is quiet effective, robust and satisfactory in real-time performance.

Template Guided Live Wire and Its Application on Automatic Extraction of Tongue in Digital Image

In this paper, we propose a novel automatic object extraction algorithm, named the Template Guided Live Wire, based on the popularly used live-wire techniques. We discuss in details the novel method’s applications on tongue extraction in digital images. With the guides of a given template curve which approximates the tongue’s shape, our method can finish the extraction of tongue without any human intervention. In the paper, we also discussed in details how the template guides the live wire, and why our method functions more effectively than other boundary based segmentation methods especially the snake algorithm. Experimental results on some tongue images are as well provided to show our method’s better accuracy and robustness than the snake algorithm.

Research on the Natural Image Classification and Segmentation Algorithm based on GPU and Neural Network

In this paper, we conduct research on the natural image classification and segmentation algorithm based on GPU and neural network. The application of image segmentation is very broad, almost appeared in all areas related to image processing, and involved in various types. With the fast development of computing technology and integrated circuit technology, the renewal speed of graphics hardware. Our method combines the GPU with network to optimize the traditional image segmentation and classification methods which will be meaningful. In the future, we will focus our attention on the hardware deployment of the GPU to modify the current approach.

A Novel Approach for Unsupervised Segmentation of Homogeneous Regions in Gray-scale Images

An improved approach for JSEG is presented for unsupervised segmentation of homogeneous regions in gray-scale images. Instead of intensity quantization, an automatic classification method based on scale space-based clustering is used for nonparametric clustering of image data set. Then EM algorithm with classification achieved by space-based classification scheme as initial data used to achieve Gaussian mixture modelling of image data set that is utilized for the calculation of soft J value. Original region growing algorithm is then used to segment the image based on the multiscale soft J-images. Experiments show that the new method can overcome the limitations of JSEG successfully.

A Fast Underwater Optical Image Segmentation Algorithm Based on a Histogram Weighted Fuzzy C-means Improved by PSO

The S/N of an underwater image is low and has a fuzzy edge.If using traditional methods to process it directly,the result is not satisfying.Though the traditional fuzzy C-means algorithm can sometimes divide the image into object and background,its time-consuming computation is often an obstacle.The mission of the vision system of an autonomous underwater vehicle (AUV) is to rapidly and exactly deal with the information about the object in a complex environment for the AUV to use the obtained result to execute the next task.So,by using the statistical characteristics of the gray image histogram,a fast and effective fuzzy C-means underwater image segmentation algorithm was presented.With the weighted histogram modifying the fuzzy membership,the above algorithm can not only cut down on a large amount of data processing and storage during the computation process compared with the traditional algorithm,so as to speed up the efficiency of the segmentation,but also improve the quality of underwater image segmentation.Finally,particle swarm optimization (PSO) described by the sine function was introduced to the algorithm mentioned above.It made up for the shortcomings that the FCM algorithm can not get the global optimal solution.Thus,on the one hand,it considers the global impact and achieves the local optimal solution,and on the other hand,further greatly increases the computing speed.Experimental results indicate that the novel algorithm can reach a better segmentation quality and the processing time of each image is reduced.They enhance efficiency and satisfy the requirements of a highly effective,real-time AUV.

Different Criteria for the Optimal Number of Clusters and Selection of Variables with R

One of the most important problems of clustering is to define the number of classes. In fact, it is not easy to find an appropriate method to measure whether the cluster configuration is acceptable or not. In this paper we propose a possible and non-automatic solution considering different criteria of clustering and comparing their results. In this way robust structures of an analyzed dataset can be often caught （or established） and an optimal cluster configuration, which presents a meaningful association, may be defined. In particular, we also focus on the variables which may be used in cluster analysis. In fact, variables which contain little clustering information can cause misleading and not-robustness results. Therefore, three algorithms are employed in this study： K-means partitioning methods, Partitioning Around Medoids （PAM） and the Heuristic Identification of Noisy Variables （HINoV）. The results are compared with robust methods ones.