A new ellipse fitting method of the minimum differential-mode noise in the atom interference gravimeter

Ellipse fitting is a useful tool to obtain the differential signal of two atom interference gravimeters. The quality standard of ellipse fitting should be the deviation between the true phase and the fitting phase of the interference fringe. In this paper, we present a new algorithm to fit the ellipse. The algorithm is to minimize the differential noise of two interference gravimeters and obtain a more accurate value of the gravity gradient. We have theoretically derived the expression of the differential-mode noise and implemented the ellipse fitting in the program. This new algorithm is also compared with the classical methods.

New separation algorithm for touching grain kernels based on contour segments and ellipse fitting

A new separation algorithm based on contour segments and ellipse fitting is proposed to separate the ellipse-like touching grain kernels in digital images.The image is filtered and converted into a binary image first.Then the contour of touching grain kernels is extracted and divided into contour segments (CS) with the concave points on it.The next step is to merge the contour segments,which is the main contribution of this work.The distance measurement (DM) and deviation error measurement (DEM) are proposed to test whether the contour segments pertain to the same kernel or not.If they pass the measurement and judgment,they are merged as a new segment.Finally with these newly merged contour segments,the ellipses are fitted as the representative ellipses for touching kernels.To verify the proposed algorithm,six different kinds of Korean grains were tested.Experimental results showed that the proposed method is efficient and accurate for the separation of the touching grain kernels.

Enhanced Detection of Glaucoma on Ensemble Convolutional Neural Network for Clinical Informatics

Irretrievable loss of vision is the predominant result of Glaucoma in the retina.Recently,multiple approaches have paid attention to the automatic detection of glaucoma on fundus images.Due to the interlace of blood vessels and the herculean task involved in glaucoma detection,the exactly affected site of the optic disc of whether small or big size cup,is deemed challenging.Spatially Based Ellipse Fitting Curve Model(SBEFCM)classification is suggested based on the Ensemble for a reliable diagnosis of Glaucomain theOptic Cup(OC)and Optic Disc(OD)boundary correspondingly.This research deploys the Ensemble Convolutional Neural Network(CNN)classification for classifying Glaucoma or Diabetes Retinopathy(DR).The detection of the boundary between the OC and the OD is performed by the SBEFCM,which is the latest weighted ellipse fitting model.The SBEFCM that enhances and widens the multi-ellipse fitting technique is proposed here.There is a preprocessing of input fundus image besides segmentation of blood vessels to avoid interlacing surrounding tissues and blood vessels.The ascertaining of OCandODboundary,which characterizedmany output factors for glaucoma detection,has been developed by EnsembleCNNclassification,which includes detecting sensitivity,specificity,precision,andArea Under the receiver operating characteristic Curve(AUC)values accurately by an innovative SBEFCM.In terms of contrast,the proposed Ensemble CNNsignificantly outperformed the current methods.

A Pupil-Positioning Method Based on the Starburst Model

Human eye detection has become an area of interest in the field of computer vision with an extensive range of applications in human-computer interaction,disease diagnosis,and psychological and physiological studies.Gaze-tracking systems are an important research topic in the human-computer interaction field.As one of the core modules of the head-mounted gaze-tracking system,pupil positioning affects the accuracy and stability of the system.By tracking eye movements to better locate the center of the pupil,this paper proposes a method for pupil positioning based on the starburst model.The method uses vertical and horizontal coordinate integral projections in the rectangular region of the human eye for accurate positioning and applies a linear interpolation method that is based on a circular model to the reflections in the human eye.In this paper,we propose a method for detecting the feature points of the pupil edge based on the starburst model,which clusters feature points and uses the RANdom SAmple Consensus(RANSAC)algorithm to perform ellipse fitting of the pupil edge to accurately locate the pupil center.Our experimental results show that the algorithm has higher precision,higher efficiency and more robustness than other algorithms and excellent accuracy even when the image of the pupil is incomplete.

Grape size detection and online gradation based on machine vision

This research investigated the size detecting and online grading of Red Globe grapes using images of entire cases,rather than individual grapes.Method of ellipse fitting based on iterative least median squares was proposed and the process of grape grading includes the following four steps:stem removal from the RGB and NIR images collected by the 2-CCD camera;edge extraction by multiple methods of edge detection,image binarization,morphological processing,et al.;size determination of individual grapes by using image segmentation and ellipse fitting to calculate short axis length;Finally,grading based on the 15%downgrade principle,this means that if the case contains more than 15%of multiple grades,then the case is re-evaluated.Thirty-eight cases of Red Globe grapes were graded using these methods and 35 cases were correctly graded with an accuracy rate reaching 92.1%.The results showed that the accuracy and speed meet the requirements of grape automatic online detection.

Splitting touching cells based on concave-point and improved watershed algorithms

Splitting touching cells is important for medi- cal image processing and analysis system. In this paper, a novel strategy is proposed to separate ellipse-like or circle- like touching cells in which different algorithms are used ac- cording to the concave-point cases of touching domains. In the strategy, a concave-point extraction and contour segmen- tation methods for cells in series and in parallel are used for the images with distinct concave points, and an improved watershed algorithm with multi-scale gradient and distance transformation is adopted for the images with un-distinct or complex concave points. In order to visualize each whole cell, ellipse fitting is used to process the segments. Experimental results show that, for the cell images with distinct concave points, both of the two algorithms can achieve good separat- ing results, but the concave-point based algorithm is more ef- ficient. However, for the cell images with unobvious or com- plex concave points, the improved watershed based algorithm can give satisfying segmenting results.

Pig target tracking algorithm based on multi-channel color feature fusion

In the process of tracking the target of the pig,with the change of the size of the tracking target in the video image,the estimated tracking target scale cannot be adaptively updated in real-time,resulting in the low accuracy of the tracking target.In this study,a multi-channel color feature adaptive fusion algorithm was proposed,and the target scale of the pig was updated in real-time by utilizing the contour information of the target pig.Experiments show that the proposed algorithm had a distance precision of 89.7%and an overlap precision of 87.5%,and the average running speed of this algorithm was 50.1 fps.The robustness of the proposed algorithm in tracking target deformation and scale variation were significantly improved,which satisfies the accuracy and real-time requirements of pig target tracking.

Extracting body surface dimensions from top-view images of pigs

Continuous live weight and carcass traits estimation are important for the pig production and breeding industry.It is widely known that top-view images of a pig’s body(excluding its head and neck)reveal surface dimension parameters,which are correlated with live weight and carcass traits.However,because a pig is not constrained when an image is captured,the body does not always have a straight posture.This creates a big challenge when extracting the body surface dimension parameters,and consequently the live weight and carcass traits estimation has a high level of uncertainty.The primary goal of this study is to propose an algorithm to automatically extract pig body surface dimension parameters,with a better accuracy,from top-view pig images.Firstly,the backbone line of a pig was extracted.Secondly,lengths of line segments perpendicular to the backbone line were calculated,and then feature points on the pig’s contour line were extracted based on the lengths variation of the perpendicular line segments.Thirdly,the head and neck of the pig were removed from the pig’s contour by an ellipse.Finally,four length and one area parameters were calculated.The proposed algorithm was implemented in Matlab®(R2012b)and applied to 126 depth images of pigs.Taking the results of the manual labeling tool as the gold standard,the length and area parameters could be obtained by the proposed algorithm with an accuracy of 97.71%(SE=1.64%)and 97.06%(SE=1.82%),respectively.These parameters can be used to improve pig live weight and carcass traits estimation accuracy in the future work.

Camera Calibration with 1D Rotating Objects

In this paper,we use 1D rotating objects to calibrate camera.The calibration object has three collinear points.It is not necessary for the object to rotate around one of its endpoints as before;instead,it rotates around the middle point in a plane.In this instance,we can use two calibration constraints to compute the intrinsic parameters of a camera.In addition,when the 1D object moves in a plane randomly,the proposed technique remains valid to compute the intrinsic parameters of a camera.Experiments with simulated data as well as with real images show that our technique is accurate and robust.

Roundness measurement of cigarette based on visual information

Roundness is defined as the degree that the cross section of an object is close to a theoretical circle. In the cigarette production process, the quality and production efficiency of a cigarette are directly affected by the roundness of the un-cut cigarette. To improve the current measurement method using a charge-coupled device （CCD） sensor and measure the roundness of cigarettes in the production line, a visual detection system composed of an industrial camera and a structural light is developed. The system＇s roundness-calculation method is closer to the real environment of the cigarette roundness. In this visual system, the line-structure light shines on the cigarette with a fixed angle and height in a longitudinal section, forming a crescent-shaped spot when the industrial camera cannot capture the cigarette＇s end surface. Then, the spot is analyzed using image-processing techniques, such as a median filter and ellipse fitting, after the industrial camera captures the spot. The system with a non-contact measurement style can meet the requirements of on-line cigarette detection with stable results and high precision.

AN IMPROVED RANDOM WALK SEGMENTATION ON THE LUNG NODULES

In this paper, we proposed a semi-automatic technique with a marker indicating the target to locate and segment nodules. For the lung nodule detection, we develop a Gabor texture feature by FCM （Fuzzy C Means） segmentation. Given a marker indicating a rough location of the nodules, a decision process is followed by applying an ellipse fitting algorithm. From the ellipse mask, the foreground and background seeds for the random walk segmentation can be automatically obtained. Finally, the edge of the nodules is obtained by the random walk algorithm. The feasibility and effectiveness of the proposed method are evaluated with the various types of the nodules to identify the edges, so that it can be used to locate the nodule edge and its growth rate.