Two stage electrostatic separator for the recycling of plastics from waste electrical and electronic equipment

The aim of study was to evaluate the effectiveness of a new facility for recycling of plastics from granular waste electrical and electronic equipment. The installation consists of two sections, the products of a first tribo-aero-electrostatic separator being subsequently treated in two free-fall electrostatic separators. The tests were performed on a mixture of polycarbonate (PC) and polyamide (PA). Analysis of the purity of the products obtained was performed using a program of image processing in MATLAB. Products of very high purity (roughly 95% for both PC and PA) were obtained at a recovery rate higher than 70%.     

Unsupervised segmentation of hidden semi-Markov non-stationary chains

The Bayesian segmentation using Hidden Markov Chains (HMC) is widely used in various domains such as speech recognition, acoustics, biosciences, climatology, text recognition, automatic translation and image processing. On the one hand, hidden semi-Markov chains (HSMC), which extend HMC, have turned out to be of interest in many situations and have improved HMC-based results. On the other hand, the case of non-stationary data can pose an important problem in real-life situations, especially when the model parameters have to be estimated. The aim of this paper is to consider these two extensions simultaneously: we propose using a particular triplet Markov chain (TMC) to deal with non-stationary hidden semi-Markov chains. In addition, we consider a recent particular HSMC having the same computation complexity as the classical HMC. We propose a related parameter estimation method and the resulting unsupervised Bayesian segmentation is validated through experiments; in particular, a real radar image segmentations are provided.     

蒸发器支撑板板孔精密测量系统

建立了蒸发器支撑板板孔精密测量系统,并提出了基于边缘约束条件的轮廓参量测量方法.首先采用图像处理技术将待测目标转化为二维离散坐标点,计算其最小外接矩形并对轮廓进行预定位;然后将轮廓分割成相互重合的"扩展邻域轮廓",建立以曲率角为原则的边缘约束算法对各轮廓段精确定界,实现对轮廓参量的精密测量.实验和误差分析表明,该系统测量准确度优于0.02mm,对具有复杂轮廓的零件参量测量有参考价值.     

Image selective restoration using multi-scale variational decomposition

In this paper we propose a multi-scale variational decomposition model for image selective restoration. Firstly, we introduce a single-parameter (BV, G, L²) variational decomposition functional and theoretically analyze the relationship between the parameter and the scale of image features. And then, by replacing the fixed scale parameter with a varying sequence in the single-parameter decomposition functional, we obtain the multi-scale variational decomposition which can decompose the input image into a series of image slices of different scales. Furthermore, we show some properties and prove the convergence of the multi-scale decomposition. Finally, we introduce an alternating and iterative method based on Chambolle’s projection algorithm to numerically solve the multi-scale variational decomposition model. Experiments are conducted on both synthetic and real images to demonstrate the effectiveness of the proposed multi-scale variational decomposition. In addition, we use the multi-scale variational decomposition to achieve image selective restoration, and compare it with several state-of-the-art models in denoising application. The numerical results show that our model has better performance in terms of PSNR and SSIM indexes.     

Copy-Paste Detection Based on a SIFT Marked Graph Feature Vector

To detect copy-paste tampering, an im-proved SIFT (Scale invariant feature transform)-based al-gorithm was proposed. Maximum angle is defined and a maximum angle-based marked graph is constructed. The m arked graph feature vector is provided to each SIFT key point via discrete polar coordinate transformation. Key points are matched to detect the copy-paste tamper-ing regions. The experimental results show that the pro-posed algorithm can effectively identify and detect the ro-tated or scaled copy-paste regions, and in comparison with the methods reported previously, it is resistant to post-processing, such as blurring, Gaussian white noise and JPEG recompression. The proposed algorithm performs better than the existing algorithm to dealing with scaling transformation.     

Scanning schemes in white light Photoelasticity – Part I: Critical assessment of existing schemes

The use of white light based Three Fringe Photoelasticity (TFP)/RGB Photoelasticity has gained importance in the recent years. With recent advances in TFP, it is possible to resolve fringe orders upto twelve. The main advantage of this technique is that it requires only a single image for isochromatic demodulation, which makes it suitable especially for problems where recording multiple images is difficult. The accuracy of isochromatic data obtained using TFP/RGB Photoelasticity is dependent on the scanning scheme used to refine the data, which is necessary to incorporate fringe order continuity. In this paper, the existing scanning schemes are critically evaluated for their ability to scan the entire model domain, influence of seed point selection and noise propagation. The scanning schemes are assessed using four problems of increasing level of geometric complexity – Circular disc under compression (simply connected), bi-axially loaded cruciform specimen with an inclined crack, a thick ring subjected to internal pressure and a finite plate with a hole (multiply connected).     

Sample selection for visual domain adaptation via sparse coding

Visual domain adaptation has attracted much attention and has made great achievement in recent years. It deals with the problem of distribution divergence between source and target domains. Current methods mostly focus on transforming images from different domains into a common space to minimize the distribution divergence. However, there are many irrelevant source samples for target domain even after the transformation. In order to eliminate the irrelevant samples, we develop a sample selection algorithm using sparse coding theory. We do the sample selection in a common subspace of source and target data to find as many as relevant source samples. In the common subspace, data characteristics are preserved by using graph regularization. Therefore, we can select the most relevant samples for our target image classification task. Moreover, in order to build a discriminative classifier for the target domain, we use not only the common part of source and target domains learned in the common subspace but also the specific part of target domain. The algorithm can be extended to handle samples from multiple source domains. Experimental results show that our visual domain adaptation method on the image classification tasks can be very effective for the state-of-the-art datasets.     

Multi-scale retinex improvement for nighttime image enhancement

We propose a retinex improvement for nighttime image enhancement. Retinex is often used on images under non-uniform illumination in terms of either color or lightness and has satisfactory results to achieve color constancy and dynamic range compression. Few studies focus retinex on nighttime images, especially those under extreme conditions (i.e., images with over-lighted or extremely under-lighted areas or with noise speckles), on which retinex operation can perform badly. Original multi-scale retinex (MSR) is extremely sensitive to noise speckles that cameras produce in low light areas, and it has unsatisfactory effect on areas with normal or intensive illumination. Moreover, original MSR uses a gain-offset method for prior-to-display treatment and can lead to apparent data loss on nighttime images. This paper replaces the logarithm function in MSR with a customized sigmoid function to minimize data loss, and adapts MSR to nighttime images by merging results from sigmoid-MSR with original images. Experiments show our framework, when applied to nighttime images, can preserve areas with normal or intensive lighting and suppress noise speckles in extreme low light areas.