Search

Mathematical morphology and convolution operators are two different methods to extract the characteristics and structures of images. Over the past decades, Deep Convolutional Neural Networks (DCNN) have been proven to be more powerful than traditional image-processing approaches. In this paper, we propose a novel structure called Deep Hybrid Neural Network (DHNN) by taking advantage of the convolution and morphological neural layers. Its practical application to polyp detection in medical images is illustrated. For experimental completeness, we adopt nine polyp image datasets, including publicly available data and our own collected data. For performance comparisons, we select three backbone models. Experimental results show that our DHNN achieves the best performance in comparisons in terms of computational complexity and accurate performance. [ABSTRACT FROM AUTHOR]

This work presents a new external driving scheme that uses the current feedback method with a 3T1C pixel circuit. The proposed circuit provides a stable OLED driving current by compensating for the threshold voltage shift of amorphous-silicon thin-film transistors (a-Si TFTs). For fabricated a-Si TFTs and the 0.35 \mum CMOS process associated with the proposed driving scheme, measurements reveal that the normalized OLED current degradation is less than 5% after 60 hours of operation at 60 ^\circC. Moreover, for a data line load of 1.69 K\Omega/110 pF, the relative error rates between data currents and OLED currents are less than 4% within a settling time of 19 \mu\s. [ABSTRACT FROM PUBLISHER]