Haar-like Feature Extraction Research Articles

Location detection of key areas in medical images based on Haar-like fusion contour feature learning.

BACKGROUND: Key area location is an important content of medical image processing and an important detail of auxiliary medical diagnosis.OBJECTIVE: In this paper, a prior knowledge fusion method based on Haar-like feature and contour feature is proposed to locate and detect key areas in medical images.METHOD: For the image to be processed, six Haar-like features and five contour features are extracted respectively. The improvement of Haar-like feature extraction template better adapts to the complexity of regional structure of medical images. The design of the contour feature extraction process fully reflects the consideration of feature invariance. The two features, together with prior knowledge, are fed into their respective decision makers and final fusers as the basis for determining and locating key regions.RESULTS: The experimental results show that the proposed method has excellent performance in locating key regions of medical images on MRI. When the capacity of the database increases from 10 to 200, the accuracy of locating the key areas of the image to be processed still reaches more than 90%.CONCLUSION: The proposed method realizes the accurate location of the key areas of medical images, which is of great significance for the auxiliary medical diagnosis.

Research on defect detection method for high-reflective-metal surface based on high dynamic range imaging

The high dynamic range imaging (HDRI) technology can realistically reproduce the scene and acquire more image information for analysis and processing. In this paper, a defect detection method based on HDRI is proposed to solve the visual inspection problem of industrial parts with high-reflective surface. Firstly, a fast calibration method is put forward to increase the calibration speed of the camera response function (CRF). Then, a novel algorithm named adaptive tone mapping based on color correction model in gradient domain is designed to adaptively adjust image chromaticity information. Finally, adaptive threshold segmentation and Haar-like feature extraction algorithm are used to detect surface defects in synthesized high dynamic range (HDR) images. The experimental results show that the HDR images processed by our algorithm can meet the detection requirements for high-reflective-metal surface. The number of sampling points required by our fast calibration algorithm of CRF is 1/10 times than that of the traditional algorithm, and the running time in the program is about 1/4 times than that of the traditional algorithm. What’s more, our improved local tone mapping algorithm is obviously improved in information entropy, contrast and average gradient.

GUI Control with Head Gesture

Face detection based mouse movement is one of the important works for the physically challenged people. The movement of head can notify the computer specific task. By understanding, the disabled people computer can pass message to other person and that can help disabled to notify others the urgent need of them. In this project, an application has been built which will help the people who do not have any control of their hands but they can only move their head. In this work, OpenCV based Haar-like feature extraction has been used to detect face. By using face detection algorithm, faces as well as non-faces are classified as faces. So, to reduce the false positive results, face detection algorithm has been enhanced. After face detection, mouse movement has been controlled with the coordinate of face movement.

Low-power coprocessor for Haar-like feature extraction with pixel-based pipelined architecture

Intelligent analysis of image and video data requires image-feature extraction as an important processing capability for machine-vision realization. A coprocessor with pixel-based pipeline (CFEPP) architecture is developed for real-time Haar-like cell-based feature extraction. Synchronization with the image sensor’s pixel frequency and immediate usage of each input pixel for the feature-construction process avoids the dependence on memory-intensive conventional strategies like integral-image construction or frame buffers. One 180 nm CMOS prototype can extract the 1680-dimensional Haar-like feature vectors, applied in the speeded up robust features (SURF) scheme, using an on-chip memory of only 96 kb (kilobit). Additionally, a low power dissipation of only 43.45 mW at 1.8 V supply voltage is achieved during VGA video procession at 120 MHz frequency with more than 325 fps. The Haar-like feature-extraction coprocessor is further evaluated by the practical application of vehicle recognition, achieving the expected high accuracy which is comparable to previous work.

Defect detection in multi-crystal solar cells using clustering with uniformity measures

Solar cells that convert sunlight into electrical energy are the main component of a solar power system. Quality inspection of solar cells ensures high energy conversion efficiency of the product. The surface of a multi-crystal solar wafer shows multiple crystal grains of random shapes and sizes. It creates an inhomogeneous texture in the surface, and makes the defect inspection task extremely difficult. This paper proposes an automatic defect detection scheme based on Haar-like feature extraction and a new clustering technique. Only defect-free images are used as training samples. In the training process, a binary-tree clustering method is proposed to partition defect-free samples that involve tens of groups. A uniformity measure based on principal component analysis is evaluated for each cluster. In each partition level, the current cluster with the worst uniformity of inter-sample distances is separated into two new clusters using the Fuzzy C-means. In the inspection process, the distance from a test data point to each individual cluster centroid is computed to measure the evidence of a defect. Experimental results have shown that the proposed method is effective and efficient to detect various defects in solar cells. It has shown a very good detection rate, and the computation time is only 0.1s for a 550×550 image.

NEW VEHICLE DETECTION ALGORITHM USING SYMMETRY SEARCH AND GA-BASED SVM

In this paper, we present a two-stage vision-based approach to detect front and rear vehicle views in road scene images. The first stage is hypothesis generation (HG), in which potential vehicles are hypothesized. During the HG step, we use a vertical, horizontal edge map, and different colors between road background and the lower part of vehicle to determine the bottom position of the vehicle. Next, we apply vertical symmetry axis detection into contour edge images to build the potential regions where vehicles may be presented. The second stage is hypothesis verification (HV). In this stage, all hypotheses are verified by Decision Tree (DT) training combined with a modified Genetic Algorithm (GA) to find the best features subset based on Haar-like feature extraction and an appropriate parameters set of Support Vector Machine for classification, which is robust for front and rear views of vehicle detection and recognition problems.

Haar-like 특징을 이용한 고성능 보행자 및 차량 인식 회로 설계

본 논문은 Haar-like 특징을 이용한 고성능 보행자 및 차량 인식 회로를 제안한다. 제안하는 회로는 영상의 매 프레임 마다 슬라이딩 윈도우를 적용하여 Haar-like 특징을 추출하고 보행자 및 차량을 인식한다. Haar-like 특징 추출 회로는 슬라이딩 윈도우 당 200개의 Haar-like 특징을 추출하며, 추출된 특징들은 AdaBoost 인식 회로에서 사용된다. 제안하는 회로는 속도 향상을 위해 병렬 회로 구조를 적용하였으며 두 개의 슬라이딩 윈도우가 동시에 보행자 또는 차량을 인식한다. 제안하는 고성능 보행자 및 차량 인식 회로는 Verilog HDL로 설계하였으며 130nm 표준 셀 라이브러리를 이용하여 게이트 수준의 회로로 합성하였다. 합성된 회로는 1,388,260개의 게이트로 구성되며 최대 동작 주파수는 203MHz이다. 제안하는 회로는 <TEX>$640{\times}480$</TEX> 영상을 초당 약 47.8장 처리할 수 있기 때문에 보행자와 차량을 실시간으로 인식하기 위해 사용될 수 있다. This paper describes the design of high-performance pedestrian and vehicle detection circuit using the Haar-like features. The proposed circuit uses a sliding window for every image frame in order to extract Haar-like features and to detect pedestrians and vehicles. A total of 200 Haar-like features per sliding window is extracted from Haar-like feature extraction circuit and the extracted features are provided to AdaBoost classifier circuit. In order to increase the processing speed, the proposed circuit adopts the parallel architecture and it can process two sliding windows at the same time. We described the proposed high-performance pedestrian and vehicle detection circuit using Verilog HDL and synthesized the gate-level circuit using the 130nm standard cell library. The synthesized circuit consists of 1,388,260 gates and its maximum operating frequency is 203MHz. Since the proposed circuit processes about 47.8 <TEX>$640{\times}480$</TEX> image frames per second, it can be used to provide the real-time detection of pedestrians and vehicles.

Fast pedestrian detection system with a two layer cascade of classifiers

This work presents a novel pedestrian detection system that uses Haar-like feature extraction and a covariance matrix descriptor to identify the distinctions of pedestrians. An approach that adopts an integral image is also applied to reduce the computational loads required in both the Haar-like feature extraction and evaluation of the covariance matrix descriptor. Based on the Fisher linear discriminant analysis (FLDA) classification algorithm, the proposed system can classify pedestrians efficiently. Additionally, the detection procedure of the proposed system is accelerated using a two-layer cascade of classifiers. The front end, constructed based on Haar-like features, can select candidate regions quickly wherever pedestrians may be present. Moreover, the back end, constructed based on the covariance matrix descriptor, can determine accurately whether pedestrians are positioned in candidate regions. If a region tests positive through the two-layer cascade classifiers, pedestrian images are likely captured.Test video sequences during the experiments are taken from a test set of the INRIA person database, using 30 input frames per second, each with a resolution of 320×240 pixels. Experimental results demonstrate that the proposed system can detect pedestrians efficiently and accurately, significantly contributing to efforts to develop a real time system.

An adaptive non-local means filter for denoising live-cell images and improving particle detection

Fluorescence imaging of dynamical processes in live cells often results in a low signal-to-noise ratio. We present a novel feature-preserving non-local means approach to denoise such images to improve feature recovery and particle detection. The commonly used non-local means filter is not optimal for noisy biological images containing small features of interest because image noise prevents accurate determination of the correct coefficients for averaging, leading to over-smoothing and other artifacts. Our adaptive method addresses this problem by constructing a particle feature probability image, which is based on Haar-like feature extraction. The particle probability image is then used to improve the estimation of the correct coefficients for averaging. We show that this filter achieves higher peak signal-to-noise ratio in denoised images and has a greater capability in identifying weak particles when applied to synthetic data. We have applied this approach to live-cell images resulting in enhanced detection of end-binding-protein 1 foci on dynamically extending microtubules in photo-sensitive Drosophila tissues. We show that our feature-preserving non-local means filter can reduce the threshold of imaging conditions required to obtain meaningful data.