Search

Taking Uyghur character recognition as an example, this paper use a method of image segmentation which combines traditional methods with CNN, and transforms and implements the Uyghur character on intelligent devices. Firstly, after analyzing the application of several general segmentation methods, this paper finds some shortcomings but also some ideas for Uighur segmentation. Then, starting from the characteristics of Uyghur language, such as structure, word formation and input habits, the author studies the idea of Uyghur adhesive language segmentation from the perspective of language characteristics, puts forward the basic algorithm of Uyghur symbol segmentation, and applies the Uyghur character adhesion segmentation based on minimum spanning tree and multi-queue primitive merging model to improve the segmentation efficiency. In addition, in order to solve the limitations of the traditional handwriting recognition framework of "preprocessing + feature extraction + classifier", this paper puts forward a new solution of Uyghur handwriting recognition technology combining prior domain knowledge with CNN, constructs a Uyghur handwriting recognition model on the basis of CNN and random elastic deformation, and also improves the recognition rate of the system by combining domain knowledge with CNN. According to the experimental results, we can conclude that the mixed method proposed in this paper can effectively break the technical bottleneck of traditional methods, thus improving the efficiency of segmentation and recognition. [ABSTRACT FROM AUTHOR]

In order to solve the problem of noise sensitivity and low precision in image segmentation, a new image segmentation method based on super-pixel with neighborhood constrained and multi-level FCM clustering is proposed. Firstly, an improved SLIC algorithm of FCM is designed based on the local pixel region of the image to get the refined super-pixel. Then, the improved FCM clustering algorithm is combined with the spatial relationship of neighborhood super-pixel to mark the super-pixel categories. In order to verify the effectiveness of the algorithm, the artificial synthetic image with noise and natural image without noise are used for comparison experiments. The experimental result show the algorithm proposed in this paper can not only suppress the noise, but also improve the processing accuracy. [ABSTRACT FROM AUTHOR]

Since rail images are normally uneven gray-scale distributed, both Otsu algorithm and VEM algorithm are therefore difficult to recognize the defects from the background. This paper proposed a VEM (valley-emphasis enhancement) algorithm based on neighborhood mean weighting. First of all, according to the image histogram, calculate the effective traversal interval, and then divide the image into two types by using threshold histogram, and the between-class variance. Secondly, calculates the threshold of neighborhood average probability, with the neighborhood average weighted variance between classes. Generally, in the most efficient traverse range obtained between-class variance and the corresponding threshold value is the optimal threshold, that not only ensure maximizing variance between images, but also meet the best threshold value fell in the bottom of the histogram. Experimental results demonstrate that the algorithm proposed in this paper can segment rail images effectively, which is superior to Otsu algorithm and VEM algorithm in image segmentation performance, and has a certain degree of improvement on anti-noise. It has better image segmentation performance for histogram images with single peak distribution and double peak distribution, and expands the application scope of the algorithm. [ABSTRACT FROM AUTHOR]

The background segmentation of human motion images is the first step in the process of human motion analysis. It is the low-level processing part of human motion analysis. The processing effect at this stage directly affects the progress of the follow-up work. The segmentation results have a great impact on the final human motion analysis results. An important purpose of our research is to endow the computer with the ability being similar to the human vision. So, the computer can feel the motion object in the view and apprehend the behavior of the human more easily. The paper is studied on the representative theories and algorithms of the background subtraction with human motion monocular image. And this paper analyses the predominance and deficiency of these theories and algorithm. These algorithms include differential images, Running Gaussian average, the Mixture of Gaussians and BP neural network. The basic principle and steps of realization are expounded. Also the data of the evaluation is given. Experiment shows that the proposed algorithm of background subtraction is highly effective and it can cast the reflected light, shadow and inverted image well. The algorithm improves the correct rate of target segmentation and is suitable for human motion image segmentation in this complex ice field environment. [ABSTRACT FROM AUTHOR]

Each pixel can be classified in the image by the semantic segmentation. The segmentation detection results of pixel level can be got which are similar to the contour of the target object. However, the results of semantic segmentation trained by Fully convolutional networks often lead to the loss of detail information. This paper proposes a CRF-FCN model based on CRF optimization. Firstly, the original image is detected based on feature pyramid networks, and the target area information is extracted, which is used to train the high-order potential function of CRF. Then, the high-order CRF is used as the back-end of the complete convolution network to optimize the semantic image segmentation. The algorithm comparison experiment shows that our algorithm makes the target details more obvious, and improves the accuracy and efficiency of semantic segmentation. [ABSTRACT FROM AUTHOR]

Image inpainting is an effective method to repair damaged image. In this paper, we mainly studied some typical image inpainting models and analyzed these corresponding repair qualities. Firstly, we studied three typical algorithms based on PDE (Partial Differential Equation) model to repair images whose damaged areas are relative small. And then we studied the image inpainting algorithm based on texture synthesis. This kind of inpainting algorithm is suitable for image with large damaged area. Finally, we studied Criminisi inpainting algorithm based on image segmentation in detail, on which we proposed an improved priority formula image repair algorithm, the simulation results indicate that the improved algorithm of this paper showed better performance in repair quality from both subjective and objective aspects. [ABSTRACT FROM AUTHOR]

In this paper, we present alternative Kernelized FCM algorithms (KFCM) that could improve magnetic resonance imaging (MRI) segmentation. Then we implement the proposed KFCM method with considering some spatial constraints on the objective function. The algorithms incorporate spatial information into the membership function and the validity procedure for clustering. We use the intra-cluster distance measure, which is simply the median distance between a point and its cluster centre. The number of the cluster increases automatically according the value of intra-cluster, for example when a cluster is obtained, it uses this cluster to evaluate intra-cluster of the next cluster as input to the KFCM and so on, stop only when intra-cluster is smaller than a prescribe value. The most important aspect of the proposed algorithms is actually to work automatically. Alterative is to improve automatic image segmentation. These methods are applied on two different sets: reference images, for objective evaluation based on estimation of segmentation accuracy and time, and non reference images, for objective evaluation based on combined judgment of opinions of specialists. [ABSTRACT FROM AUTHOR]