Wei-Yao Chiu

Defect Detection in Solar Modules Using ICA Basis Images

Solar power has become an attractive alternative of electricity energy. Solar cells that form the basis of a solar power system are mainly based on multicrystalline silicon. A set of solar cells are assembled and interconnected into a large solar module to offer a large amount of electricity power for commercial applications. Many defects in a solar module cannot be visually observed with the conventional CCD imaging system. This paper aims at defect inspection of solar modules in electroluminescence (EL) images. The solar module charged with electrical current will emit infrared light whose intensity will be darker for intrinsic crystal grain boundaries and extrinsic defects including micro-cracks, breaks and finger interruptions. The EL image can distinctly highlight the invisible defects but also create a random inhomogeneous background, which makes the inspection task extremely difficult. The proposed method is based on independent component analysis (ICA), and involves a learning and a detection stage. The large solar module image is first divided into small solar cell subimages. In the training stage, a set of defect-free solar cell subimages are used to find a set of independent basis images using ICA. In the inspection stage, each solar cell subimage under inspection is reconstructed as a linear combination of the learned basis images. The coefficients of the linear combination are used as the feature vector for classification. Also, the reconstruction error between the test image and its reconstructed image from the ICA basis images is also evaluated for detecting the presence of defects. Experimental results have shown that the image reconstruction with basis images distinctly outperforms the ICA feature extraction approach. It can achieve a mean recognition rate of 93.4% for a set of 80 test samples.

Motion detection using Fourier image reconstruction

In video surveillance, detection of moving objects from an image sequence is very important for object tracking, activity recognition and behavior understanding. The conventional background subtraction suffers from slow updating of environmental changes, and temporal difference cannot accurately extract the moving object boundaries. In this paper, a Fourier reconstruction scheme for motion detection is proposed. A series of consecutive 2D spatial images along the time axis are first reorganized as a series of 2D spatial-temporal images along a spatial axis. In each of the 2D spatial-temporal images, a static background region forms a vertical line pattern, and a moving object creates an irregular, non-vertical structure in the image. Fourier transforms are applied to remove the vertical line pattern (i.e. the background) and retain only the foreground in the reconstructed image. The proposed method is a global approach that identifies the moving objects based on structural variations in the whole patterned image. It is therefore very robust to accommodate noise and local gray-level variations. It can well extract the shapes of foreground objects at various moving speeds, and is very responsive to dynamic environments. High computational cost is the major drawback of the proposed method. However, it can still achieve 11 frames per second for small images of size 150x200.

Anisotropic diffusion-based detail-preserving smoothing for image restoration

It is important in image restoration to remove noise while preserving meaningful details such as edges and fine features. The existing edge-preserving smoothing methods may inevitably take fine detail as noise or vice versa. In this paper, we propose a new edge-preserving smoothing technique based on a modified anisotropic diffusion. The proposed method can simultaneously preserve edges and fine details while filtering out noise in the diffusion process. Since the fine detail in the neighborhood of a small image window generally have a gray-level variance larger than that of the noisy background, the proposed diffusion model incorporates both local gradient and gray-level variance to preserve edges and fine details while effectively removing noise. Experimental results have shown that the proposed anisotropic diffusion scheme can effectively smooth noisy background, yet well preserve edge and fine details in the restored image. The proposed method has the best restoration result compared with other edge-preserving methods.

Dual-mode detection for foreground segmentation in low-contrast video images

In video surveillance, the detection of foreground objects in an image sequence from a still camera is critical for object tracking, activity recognition, and behavior understanding. The widely used background updating models such as single Gaussian and mixture of Gaussians are based mainly on the mean gray level of a given observation period, which could be inevitably affected by outliers and noise in the images. The mean from the average of background pixel values and foreground pixel values of consecutive image frames in an observed period will not represent the true background in the scene. Thus, the mean background models cannot detect low-contrast objects and promptly respond to sudden light changes. In this paper, a dual-mode scheme for foreground segmentation is proposed. The mode is based on the most frequently occurring gray level of observed consecutive image frames, and is used to represent the background in the scene. In order to accommodate the dynamic changes of a background, the proposed method uses a dual-mode model for background representation. The dual-mode model can represent two main states of the background and detect a more complete silhouette of the foreground object in the dynamic background. The proposed method can promptly calculate the exact gray level mode of individual pixels in image sequences by simply dropping the last image frame and adding the current image in an observed period. The comparative evaluation of foreground segmentation methods is performed on the Microsoft’s Wallflower dataset. The results show that the proposed method can quickly respond to illumination changes and well extract foreground objects in a low-contrast background.

3-D vision-assist guidance for robots or the visually impaired

– This study aims to propose a door detection method based on the door properties in both depth and gray-level images. It can further help blind people (or mobile robots) find the doorway to their destination. , – The proposed method uses the hierarchical point–line region principle with majority vote to encode the surface features pixel by pixel, and then dominant scene entities line by line, and finally the prioritized scene entities in the center, left and right of the observed scene. , – This approach is very robust for noise and random misclassification in pixel, line and region levels and provides sufficient information for the pathway in the front and on the left and right of a scene. The proposed robot vision-assist system can be worn by visually impaired people or mounted on mobile robots. It provides more complete information about the surrounding environment to guide safely and effectively the user to the destination. , – In this study, the proposed robot vision scheme provides detailed configurations of the environment encountered in daily life, including stairs (up and down), curbs/steps (up and down), obstacles, overheads, potholes/gutters, hazards and accessible ground. All these scene entities detected in the environment provide the blind people (or mobile robots) more complete information for better decision-making of their own. This paper also proposes, especially, a door detection method based on the door’s features in both depth and gray-level images. It can further help blind people find the doorway to their destination in an unfamiliar environment.

A macro-observation scheme for abnormal event detection in daily-life video sequences

We propose a macro-observation scheme for abnormal event detection in daily life. The proposed macro-observation representation records the time-space energy of motions of all moving objects in a scene without segmenting individual object parts. The energy history of each pixel in the scene is instantly updated with exponential weights without explicitly specifying the duration of each activity. Since possible activities in daily life are numerous and distinct from each other and not all abnormal events can be foreseen, images from a video sequence that spans sufficient repetition of normal day-to-day activities are first randomly sampled. A constrained clustering model is proposed to partition the sampled images into groups. The new observed event that has distinct distance from any of the cluster centroids is then classified as an anomaly. The proposed method has been evaluated in daily work of a laboratory and BEHAVE benchmark dataset. The experimental results reveal that it can well detect abnormal events such as burglary and fighting as long as they last for a sufficient duration of time. The proposed method can be used as a support system for the scene that requires full time monitoring personnel.

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.

A Generalized Anisotropic Diffusion for Defect Detection in Low-Contrast Surfaces

In this paper, an anisotropic diffusion model with a generalized diffusion coefficient function is presented for defect detection in low-contrast surface images and, especially, aims at material surfaces found in liquid crystal display (LCD) manufacturing. A defect embedded in a low-contrast surface image is extremely difficult to detect because the intensity difference between unevenly-illuminated background and defective regions are hardly observable. The proposed anisotropic diffusion model provides a generalized diffusion mechanism that can flexibly change the curve of the diffusion coefficient function. It adaptively carries out a smoothing process for faultless areas and performs a sharpening process for defect areas in an image. An entropy criterion is proposed as the performance measure of the diffused image and then a stochastic evolutionary computation algorithm, particle swarm optimization (PSO), is applied to automatically determine the best parameter values of the generalized diffusion coefficient function. Experimental results have shown that the proposed method can effectively and efficiently detect small defects in low-contrast surface images.

Surface defect detection of 3D objects using robot vision

Purpose – The purpose of this paper is to develop a robot vision system for surface defect detection of 3D objects. It aims at the ill‐defined qualitative items such as stains and scratches.Design/methodology/approach – A robot vision system for surface defect detection may counter: high surface reflection at some viewing angles; and no reference markers in any sensed images for matching. A filtering process is used to separate the illumination and reflection components of an image. An automatic marker‐selection process and a template‐matching method are then proposed for image registration and anomaly detection in reflection‐free images.Findings – Tests were performed on a variety of hand‐held electronic devices such as cellular phones. Experimental results show that the proposed system can reliably avoid reflection surfaces and effectively identify small local defects on the surfaces in different viewing angles.Practical implications – The results have practical implications for industrial objects with ...

A Macro-observation Approach of Intelligence Video Surveillance for Real-Time Unusual Event Detection

In this paper, we propose a macro-observation scheme for unusual event detection in daily life, where motions in time-space domain are described by a global representation and individual activities do not have to be defined and modeled beforehand. The proposed representation records the time-space energy of motions of all moving objects in a scene without segmenting individual object parts or tracking objects. In daily life, images from a video sequence that spans sufficient repetition of normal day-to-day activities are first randomly sampled. A hierarchical fuzzy C-means clustering is used to divide the sampled images into groups. The goal of clustering is to assign similar training samples to the same cluster so that the distance of every member in the cluster to the cluster center meets a minimum distance threshold. The new observed event that has distinct distance from any of the cluster centroids is then classified as an anomaly. The proposed method has been evaluated in daily work of a laboratory and a convenience store. In order to test the robustness of the proposed method for unusual events detection in daily life, the laboratory scene was continuously monitored for 31 days. The experimental results reveal that the proposed method can well detect unusual events such as fighting as long as they last for a sufficient duration of time.