Xiaomao Liu

SVM based ultrasonic medicine image diagnosis

The technique of support vector machines (SVMs) has been used as a new method for solving classification, regression, time series prediction and function estimation problems with many successful applications. In this paper, we use SVM to solve the problem of classification for ultrasonic medicine image. We use statistical characteristics of the interesting part in an ultrasonic image to aid a doctor to give a correct diagnosis. The procedure is: first, to extract a number of small sampling regions in the interesting part; second, to calculate a series of moments about those sampling regions; third, to decide whether the interesting part of the organ is normal or abnormal according to the analyses of the series of moments based on SVM. SVMs structural risk minimization principle is the guarantee that the diagnosis has the minimum mistake probability. The diagnosis based on SVM is optimal from the viewpoint of structural risk minimization principle. It is hoped that the results presented here will be helpful to the diagnosis based on ultrasonic medicine image.

A localization algorithm of adaptively determining the ROI of the reference circle in image

Aiming at solving the problem of accurately positioning the detection probes underwater, this paper proposed a method based on computer vision which can effectively solve this problem. The theory of this method is that: First, because the shape information of the heat tube is similar to a circle in the image, we can find a circle which physical location is well known in the image, we set this circle as the reference circle. Second, we calculate the pixel offset between the reference circle and the probes in the picture, and adjust the steering gear through the offset. As a result, we can accurately measure the physical distance between the probes and the under test heat tubes, then we can know the precise location of the probes underwater. However, how to choose reference circle in image is a difficult problem. In this paper, we propose an algorithm that can adaptively confirm the area of reference circle. In this area, there will be only one circle, and the circle is the reference circle. The test results show that the accuracy of the algorithm of extracting the reference circle in the whole picture without using ROI (region of interest) of the reference circle is only 58.76% and the proposed algorithm is 95.88%. The experimental results indicate that the proposed algorithm can effectively improve the efficiency of the tubes detection.

Method of segmenting river from remote sensing image

This paper presents a method of segment the river area in remote sensing images. The spectral distribution of the river area in the image is relatively uniform, and the overall gray level is dark, And the spectrum is evenly distributed regardless of direction, but land area spectral information is very messy, most of the land in the regional spectral distribution is not uniform, maybe some land area spectral distribution is more uniform, but has a certain direction, this paper according to these characteristics, using the cross-type template, the regional variance is used as the regional texture characteristic to obtain the adaptive threshold to obtain the adaptive binary graph. The river is usually a connected water, only a large enough area to determine the river, so the use of binary image marking algorithm to obtain the largest connected area, marked as a river. This paper presents the method of river segmentation. Experiments show that the river segmentation is suitable for remote sensing images with relatively large river regions.

The method for froth floatation condition recognition based on adaptive feature weighted

The fusion of foam characteristics can play a complementary role in expressing the content of foam image. The weight of foam characteristics is the key to make full use of the relationship between the different features. In this paper, an Adaptive Feature Weighted Method For Froth Floatation Condition Recognition is proposed. Foam features without and with weights are both classified by using support vector machine (SVM).The classification accuracy and optimal equaling algorithm under the each ore grade are regarded as the result of the adaptive feature weighting algorithm. At the same time the effectiveness of adaptive weighted method is demonstrated.

The selection of the optimal baseline in the front-view monocular vision system

In the front-view monocular vision system, the accuracy of solving the depth field is related to the length of the inter-frame baseline and the accuracy of image matching result. In general, a longer length of the baseline can lead to a higher precision of solving the depth field. However, at the same time, the difference between the inter-frame images increases, which increases the difficulty in image matching and the decreases matching accuracy and at last may leads to the failure of solving the depth field. One of the usual practices is to use the tracking and matching method to improve the matching accuracy between images, but this algorithm is easy to cause matching drift between images with large interval, resulting in cumulative error in image matching, and finally the accuracy of solving the depth field is still very low. In this paper, we propose a depth field fusion algorithm based on the optimal length of the baseline. Firstly, we analyze the quantitative relationship between the accuracy of the depth field calculation and the length of the baseline between frames, and find the optimal length of the baseline by doing lots of experiments; secondly, we introduce the inverse depth filtering technique for sparse SLAM, and solve the depth field under the constraint of the optimal length of the baseline. By doing a large number of experiments, the results show that our algorithm can effectively eliminate the mismatch caused by image changes, and can still solve the depth field correctly in the large baseline scene. Our algorithm is superior to the traditional SFM algorithm in time and space complexity. The optimal baseline obtained by a large number of experiments plays a guiding role in the calculation of the depth field in front-view monocular.

The improvement of VIBE foreground detection algorithm

VIBE algorithm is one of the effective methods that based on dynamic model, which can deal with the detection of moving objects in the slowly changing background. The traditional VIBE uses a fixed threshold to realize target cutting ,that would result in a poor detection when the target enters a background area whose pixel value is not much different from its own pixel value.Thus,we propose a method of moving target detection based on dynamic threshold in this paper.

An image rectification method on image sequence of monocular motion vision

Image rectification reduce the search space from 2-dimension to 1-dimension and improve the searching efficiency of stereo matching algorithm greatly. In this paper, a simple and convenient method, which fully considered image sequence of monocular motion vision, is proposed to rectify the calibrated image sequence. The method is based on coordinate system transformation, which can avoid the mass and complex computations, and the method rectifies image sequence (three images) at once, which is efficient in image sequence processing. In this method, the rectification is composed of several steps. Firstly, we establish a reference coordinate system by three movement position. The Z axis of the reference coordinate system o_XYZ is the normal vector of the plane which three positions located. The direction of X axis coincides with the baseline from position 2 to position 1. We set Y axis according to right-hand principle. Secondly, we set the x axis and z axis of reference image space coordinate system o_xyz coincides with the X axis and Z axis of the reference coordinate system, and the y axis is set to coincide with the line from position 2 to position 3. Finally, we deduce a homography matrix to realize the image rectification. Both image data and computer simulation data show that the method is an effective rectification method.

Image mosaic at pixel level

Image mosaic is brought up for improving the visual field of common camera which cannot fulfill practical requirement of ultra-wide-angle panoramic images. As widely known, to get mosaic images, two main steps should be considered, namely image alignment and stitching. Image stitching algorithms create the high-resolution photo-mosaics used to produce today’s digital maps and satellite photos. In this paper, an image stitching process to detect and eliminate the pixel merges is improved and compared with some popular image stitching algorithms.

Livewire based single still image segmentation

In the application of the video contactless measurement, the quality of the image taken from underwater is not very well. It is well known that automatic image segmental method cannot provide acceptable segmentation result with low quality single still image. Snake algorithm can provide better result in this case with the aiding of human. However, sometimes the segmental result of Snake may far from the initial segmental contour drawn by user. Livewire algorithm can keep the location of the seed points that user selected nailed from the beginning to the end. But the contour may have burrs when the images noise is quite high and the contrast is low. In this paper, we modified the cost function of Livewire algorithm and proposed a new segmentation method that can be used for single still image segmentation with high noise and low contrast.

Laser-beam-based calibration

A laser beam based calibration method is proposed in the paper. The laser beam we used can keep the cylinder shape in the real world space. The cylinder shaped laser beam will form an elliptical area in the plane in which the defect we want to measure also located. This elliptical laser area will form an ellipse in the image. Our purpose is to achieve calibration only depending on the elliptical parameters of the ellipse in the image. We created the relationship model between the elliptical parameters of the ellipse in the image and the calibration parameters of the video appliance, and we find a quick and easy way to solve the relationship model. Using this calibration method we can achieve contactless video measurement during the equipment checking in the nuclear power station.