1 November 2012 in Computer Vision and Image Understanding
7 May 2021 in IEEE Transactions on Electron Devices
In order to accelerate the semiconductor device simulation, we propose to use a neural network to learn an approximate solution for desired bias conditions. With an initial solution (predicted by a trained neural network) sufficiently close to the final one, the computational cost to calculate several unnecessary solutions is significantly reduced. Specifically, a convolutional neural network for the metal–oxide–semiconductor field-effect transistor (MOSFET) is trained in a supervised manner to compute the initial solution. In particular, we propose to consider a device template for various devices and a compact expression of the solution based on the electrostatic potential. We empirically show that the proposed method accelerates the simulation significantly.
22 November 2011 in IEEE Transactions on Image Processing
With the goal of matching unknown faces against a gallery of known people, the face identification task has been studied for several decades. There are very accurate techniques to perform face identification in controlled environments, particularly when large numbers of samples are available for each face. However, face identification under uncontrolled environments or with a lack of training data is still an unsolved problem. We employ a large and rich set of feature descriptors (with more than 70 000 descriptors) for face identification using partial least squares to perform multichannel feature weighting. Then, we extend the method to a tree-based discriminative structure to reduce the time required to evaluate probe samples. The method is evaluated on Facial Recognition Technology (FERET) and Face Recognition Grand Challenge (FRGC) data sets. Experiments show that our identification method outperforms current state-of-the-art results, particularly for identifying faces acquired across varying conditions.
14 July 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
An event camera reports per-pixel intensity differences as an asynchronous stream of events with low latency, high dynamic range (HDR), and low power consumption. This stream of sparse/dense events limits the direct use of well-known computer vision applications for event cameras. Further applications of event streams to vision tasks that are sensitive to image quality issues, such as spatial resolution and blur, e.g., object detection, would benefit from a higher resolution of image reconstruction. Moreover, despite the recent advances in spatial resolution in event camera hardware, the majority of commercially available event cameras still have relatively low spatial resolutions when compared to conventional cameras. We propose an end-to-end recurrent network to reconstruct high-resolution, HDR, and temporally consistent grayscale or color frames directly from the event stream, and extend it to generate temporally consistent videos. We evaluate our algorithm on real-world and simulated sequences and verify that it reconstructs fine details of the scene, outperforming previous methods in quantitative quality measures. We further investigate how to (1) incorporate active pixel sensor frames (produced by an event camera) and events together in a complementary setting and (2) reconstruct images iteratively to create an even higher quality and resolution in the images.