Sorry, you need to enable JavaScript to visit this website.

Photovoltaic is one of the most important renewable energy sources for dealing with world-wide steadily increasing energy consumption. This raises the demand for fast and scalable automatic quality management during production and operation. However, the detection and segmentation of cracks on electroluminescence (EL) images of mono- or polycrystalline solar modules is a challenging task. In this work, we propose a weakly supervised learning strategy that only uses image-level annotations to obtain a method that is capable of segmenting cracks on EL images of solar cells.

We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object models are rendered in 3D models of complete scenes with realistic materials and lighting, (2) plausible geometric configuration of objects and cameras in a scene is generated using physics simulation, and (3) high photorealism of the synthesized images is achieved by physically based rendering.

Accurate hand segmentation is important for human segmentation. However, in videos, hand regions usually have serious motion blur, which reduces segmentation performance obviously. To solve this problem, we propose an automatic matting network to deal with motion-blurred hands. Then we combine the hand alpha mattes provided by matting network and the human segmentation results provided by segmentation network to generate our final human soft segmentation results.

Region tracking becomes a challenging problem at the presence of low contrast and textured images such as cilia video images where beating cilia appear as moving texture. Tracking such patterns requires extracting of features that are capable of discriminating them effectively. In this paper, a method based on texture features for region tracking is proposed. The texture features are extracted from a sequence of images using Gaussian Markov Random Fields (GMRF). These features are employed to track the motion of a given region and extract its trajectory.

We address two issues for tackling face recognition across pose, one is disentangled representation learning and the other is training data augmentation. To have better training properties, we propose the Representation-Learning Wasserstein-GAN (RL-WGAN) with three component networks for learning the disentangled facial representation. As the learning based on imbalanced data often leads to biased estimation, we proposed a data augmentation scheme that exploits the 3D Morphable Model (3DMM) for generating faces of desired poses.

While current landmark detection algorithms offer a good approximation of the landmark locations, they are often unsuitable for the use in biological research. We present multimodal landmark detection approach, based on Point distribution model that detects a larger number of anthropologically relevant landmarks than the current landmark detection algorithms.
At the same time we show that improving detection accuracy of initial vertices, using image information, to which

We describe in this paper a Two-Stream Siamese Neural Network for vehicle re-identification. The proposed network is fed simultaneously with small coarse patches of the vehicle shape’s, with 96 × 96 pixels, in one stream, and fine features extracted from license plate patches, easily readable by humans, with 96 × 48 pixels, in the other one.

The bilateral filter is popularly used for image enhancement. By using a range kernel along with a spatial kernel, the filter is able to smooth images without excessive blurring of edges. It has been shown that the enhancement capacity of the filter can be boosted by adapting the width of the range kernel at each pixel. A fast algorithm for grayscale images was recently proposed for this so-called adaptive bilateral filter, which is otherwise computationally expensive. This can trivially be extended for color filtering using channelwise processing.