Eye Detection Based on Improved AdaBoost Algorithm

The face detection based on skin color features is greatly affected by illumination and the face detection based on AdaBoost algorithm is greatly affected by multi-pose of face, and this means that the large face deflection will make the detection less accurate. So we investigated a face detection method that combines the skin color model and the improved AdaBoost algorithm in this paper. This method first judges whether the collected face image needs illumination compensation. The image is converted from RGB color space to YCbCr color space with higher pixel clustering characteristics and distribution rules by whether it is needed or not. Meanwhile, the candidate regions containing face images are carried out through morphological process and shape select after establishing the Gaussian model. Finally, the face detection results are obtained through detecting the candidate regions with face images by improved AdaBoost algorithm. A large number of experimental results show that this new method can effectively reduce the false detection rate and improve the efficiency of face detection.

This paper is based on the background of learners' expression recognition in emotion recognition interactive E-Learning. This paper aims at time-consuming of training samples and weights degradation two problems of traditional AdaBoost algorithm, proposes a decile eigenvalue AdaBoost algorithm and joins FPR (False Positive Rate) in this algorithm. The experiments use improved AdaBoost algorithm in E-Learning face detection achieved good effect, and the results provide good conditions for the follow-up E-Learning expression feature extraction.

Detection and classification of DC and feeder faults in DC microgrid using new morphological operators with multi class AdaBoost algorithm

In this paper, we propose an eye detection method that is robust to facial pose changes using gradient directional features of brightness and a particle filter. The rejection function of incorrect eye detection in the proposed method allows for the eye detection again even if the eye is incorrectly detected. In this method, to estimate the boundary between the iris and sclera or eyelid, the gradient intensities are calculated by four directional Prewitt filters in four regions. The likelihood used in the particle filter is obtained by averaging the gradient intensities for the specific direction in the four regions and the upper eyelid area. From experimental results, the average detection rates of both eyes for roll, yaw, and pitch angles of the face are more than 90% by using rejection function for incorrect eye detection. The rejection function produces the 4.4%, 4.5%, and 4.9% increases in average detection rates of both eyes for roll, yaw, and pitch facial angles, respectively. The proposed eye detection method can track both eye in real-time (about 20 ms) and is robust to the facial pose changes.

Face recognition algorithm is a very promising technique in biometric authentication. However, the recognition precision can be affected by many factors, such as feature extraction method and classifier selection. In this paper, a novel algorithm for face recognition is presented according to the advances of the wavelet decomposition technique and the Support Vector Machines (SVM) model. The extracted features from human images by wavelet decomposition are less sensitive to facial expression variation. As a classifier, SVM provides high generation performance without transcendental knowledge. First, we detect the face region using an improved AdaBoost algorithm. Second, we extract the appropriate features of the face by wavelet decomposition, and compose the face feature vectors as input to SVM. Third, we train the SVM model by the face feature vectors, and then use the trained SVM model to classify the human face. In the training process, three different kernel functions are adopted: Radial basis function, Polynomial and Linear kernel function. Finally, we present a face recognition system that can achieve high recognition precision and fast recognition speed in practice. Experimental results indicate that the proposed method can achieve recognition precision of 96.78 percent based on 96 persons in Ren-FEdb database that is higher than other approaches.

IPTV is an increasingly important service for telecom operators. Service providers have to repair IPTV faults quickly in order to provide high quality service. It will be very helpful if faults can be predicted. Considering this situation, we combine status data from the set top box with the data of customer trouble tickets and then build a prediction system with improved AdaBoost to predict faults in IPTV system. First, we clean and conduct some statistical analysis for the dataset. Then, we apply feature selection to the preprocessed data and build the associated models. It is noted that we improve the AdaBoost algorithm by adding F1 measure to cost function and limiting the weights of different classifications. Our evaluation results show that the improved algorithm achieves precision of 88.89% and performs better than original AdaBoost in IPTV fault prediction.

Eye detection is the most important and critical task of diverse applications such as face detection and recognition. However, most eye detection methods do not fully consider detection robustness to people with glasses, illumination variation, head pose change, and eye occlusions. This paper proposes an efficient hybrid eye detection method based on a gray intensity variance filter (VF) and support vector machines (SVMs). Firstly, the VF is used for eliminating most of noneye region images to keep less candidate eye regions. Then accurate two eye regions are determined easily through the trained SVM classifier. Moreover, this paper provides an assessment of the sensitivity of obtained parameters in the SVM classifier on eye detection accuracy. The proposed method was evaluated on different face databases. The experimental results show that the method can improve the performance of eye detection and achieve a higher detection accuracy compared with state-of-the-art methods.

Aiming at the problem of localization of eye centers in complex scenes, a method for quickly locating eye center is proposed in this paper. For the collected face images, this paper firstly uses bilateral filtering algorithm to remove the possible noise, and performs histogram equalization operation on the gray image to increase the dynamic range of the image grayscale and improve its distinguishability. Then, constructing cascaded strong classifier based on improved Ada Boost algorithm, and proposed three-layer eye detection. Finally, the method of canny operator edge detection and improved Hough circle detection is used to obtain the pupil center. The experimental results show that the algorithm can acquire the coordinates of the eye center quickly and accurately, and it is robust to eye location under illumination changes.

As a key component in the hydraulic brake system of automobiles, the brake joint directly affects the braking performance and driving safety of the vehicle. Therefore, improving the quality of brake joints is crucial. During the processing, due to the complexity of the welding material and welding process, the weld seam is prone to various defects such as cracks, pores, undercutting, and incomplete fusion, which can weaken the joint and even lead to product failure. Traditional weld seam detection methods include destructive testing and non-destructive testing; however, destructive testing has high costs and long cycles, and non-destructive testing, such as radiographic testing and ultrasonic testing, also have problems such as high consumable costs, slow detection speed, or high requirements for operator experience. In response to these challenges, this article proposes a defect detection and classification method for laser welding seams of automotive brake joints based on machine vision inspection technology. Laser-welded automotive brake joints are subjected to weld defect detection and classification, and image processing algorithms are optimized to improve the accuracy of detection and failure analysis by utilizing the high efficiency, low cost, flexibility, and automation advantages of machine vision technology. This article first analyzes the common types of weld defects in laser welding of automotive brake joints, including craters, holes, and nibbling, and explores the causes and characteristics of these defects. Then, an image processing algorithm suitable for laser welding of automotive brake joints was studied, including pre-processing steps such as image smoothing, image enhancement, threshold segmentation, and morphological processing, to extract feature parameters of weld defects. On this basis, a welding seam defect detection and classification system based on the cascade classifier and AdaBoost algorithm was designed, and efficient recognition and classification of welding seam defects were achieved by training the cascade classifier. The results show that the system can accurately identify and distinguish pits, holes, and undercutting defects in welds, with an average classification accuracy of over 90%. The detection and recognition rate of pit defects reaches 100%, and the detection accuracy of undercutting defects is 92.6%. And the overall missed detection rate is less than 3%, with both the missed detection rate and false detection rate for pit defects being 0%. The average detection time for each image is 0.24 s, meeting the real-time requirements of industrial automation. Compared with infrared and ultrasonic detection methods, the proposed machine-vision-based detection system has significant advantages in detection speed, surface defect recognition accuracy, and industrial adaptability. This provides an efficient and accurate solution for laser welding defect detection of automotive brake joints.

In refractive eye surgery using laser, automatically localizing a target eye for surgery and precisely focusing the laser to the corneal surface are crucial to the medical treatment. We therefore propose a new eye detection method based on template matching for automatic localizations of target eyes for refractive eye surgery with excimer laser. In the proposed approach, representative templates of image gradient histograms of eyes are constructed using both open and privately-collected eye datasets. Real-time eye detection that helps guiding the excimer laser to a target eye for surgery can be achieved by the efficient template matching. After the eye localization, image-guided, automatic alignment of positioning marker, i.e., a read line of visible light, is then employed to measure the distance between the corneal surface and the excimer laser. Experimental results show that the proposed eye detection method using template matching outperforms an HoG-based eye detector in miss detection rates based on the same training data for this specific medical application. Also, with the automatic image-guided positioning of laser head, the time consuming process of manual laser focusing can be largely simplified.

BackgroundPrediction of ligand binding sites is important to elucidate protein functions and is helpful for drug design. Although much progress has been made, many challenges still need to be addressed. Prediction methods need to be carefully developed to account for chemical and structural differences between ligands.ResultsIn this study, we present ligand-specific methods to predict the binding sites of protein-ligand interactions. First, a sequence-based method is proposed that only extracts features from protein sequence information, including evolutionary conservation scores and predicted structure properties. An improved AdaBoost algorithm is applied to address the serious imbalance problem between the binding and non-binding residues. Then, a combined method is proposed that combines the current template-free method and four other well-established template-based methods. The above two methods predict the ligand binding sites along the sequences using a ligand-specific strategy that contains metal ions, acid radical ions, nucleotides and ferroheme. Testing on a well-established dataset showed that the proposed sequence-based method outperformed the profile-based method by 4–19% in terms of the Matthews correlation coefficient on different ligands. The combined method outperformed each of the individual methods, with an improvement in the average Matthews correlation coefficients of 5.55% over all ligands. The results also show that the ligand-specific methods significantly outperform the general-purpose methods, which confirms the necessity of developing elaborate ligand-specific methods for ligand binding site prediction.ConclusionsTwo efficient ligand-specific binding site predictors are presented. The standalone package is freely available for academic usage at http://dase.ecnu.edu.cn/qwdong/TargetCom/TargetCom_standalone.tar.gz or request upon the corresponding author.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1348-3) contains supplementary material, which is available to authorized users.

Traditional Adaboost face detection algorithm uses Haar-like features training face classifiers, whose detection error rate is low in the face region. While under the complex background, the classifiers will make wrong detection easily to the background regions with the similar faces gray level distribution, which leads to the error detection rate of traditional Adaboost algorithm is high. As one of the most important features of a face, skin in YCgCr color space has good clustering. We can fast exclude the non-face areas through the skin color model. Therefore, combining with the advantages of the Adaboost algorithm and skin color detection algorithm, this paper proposes Adaboost face detection algorithm method that bases on YCgCr skin color model. Experiments show that, compared with traditional algorithm, the method we proposed has improved significantly in the detection accuracy and errors.

In view of the current problems of HNIDS (high-speed network intrusion detection system), such as high packet loss rate, slow pace of testing for attacks and unbalanced data for detection. This paper presents a novel approach for HNIDS by taking two-stage strategy with load balancing model. In the on-line phase, the system captures the packets from network and split into small according the type of protocol, then detected intrusion through each sensor. In the off-line, training dataset are used to build model, which can detected intrusion. We discuss different approaches to unbalanced data, empirically evaluate the SMOTE over-sampling approaches, AdaBoost and random forests algorithm. We also discuss the approaches for selecting features. Finally report our experimental results over the KDD'99 datasets. The results show that SMOTE and the AdaBoost algorithm by using random forests as weak learner not only can provides better performance to small class, but also has lower build model time.

An innovative method for cascade eye detection using facial geometric features is proposed. The cascade detector is used to detect pairs of eye of candidates. The size similarity, the horizontal symmetry, the horizontal sextant angle, and the scale coefficients extracted from facial geometric feature are integrated to improve eye detection. Both the BioID database and real-time video stream were used in the experiments. Experimental results show that the proposed eye detection method is significantly more accurate than the cascade detector alone without sacrificing overmuch time-efficiency.

Background Even when a laboratory analyte testing process is in control, routine quality control testing will fail with a frequency that can be predicted by the number of quality control levels used, the run frequency and the control rule employed. We explored whether simply counting the number of assay quality control run failures during a running week, and then objectively determining if there was an excess, could complement daily quality control processes in identifying an out-of-control assay. Methods Binomial statistics were used to determine the threshold number of quality control run failures in any rolling week which would statistically exceed that expected for a particular test. Power function graphs were used to establish error detection (Ped) and false rejection rates compared with popular control rules. Results Identifying quality control failures exceeding the weekly limit (QC FEWL) is a more powerful means of detecting smaller systematic (bias) errors than traditional daily control rules (12s, 13s or 13s/22s/R4s) and markedly superior in detecting smaller random (imprecision) errors while maintaining false identification rates below 2%. Error detection rates also exceeded those using a within- and between-run Westgard multirule (13s/22s/41s/10x). Conclusions Daily review of tests shown to statistically exceed their rolling week limit of expected quality control run failures is more powerful than traditional quality control tools at identifying potential systematic and random test errors and so offers a supplement to daily quality control practices that has no requirement for complex data extraction or manipulation.