(a). Human visual perception system, (b). CNN model, and (c). The confusion matrix (IMAGE)
Caption
a, Schematic of the human visual-perception process: visual perception is one of the vital human senses where the brain decodes what the eyes see or sense. The human eye receives more than 80% of information through light. The brain visual-perception process is represented wherein the human eye receives light from an external source. This light is focused on the retina of the eye, which captures an image of the visual stimuli. Nerve cells present in the retina function as photoreceptors that convert light into electrical impulses. These impulses move from the optic nerve to the visual cortex at the back of the human brain. b, A small convolutional neural network (CNN) was designed to demonstrate the device's optical sensing and electrical programming abilities. For that, we extracted images from the Canadian Institute for Advanced Research (CIFAR)-10 dataset to make a simple binary image recognition, wherein the object “dog” and “automobile” were chosen as the classification tasks. The original images consists of three RGB channels of size 32×32×3, wherein each channel, discrete pixels are stored with three light intensities (Red, Green, and Blue). Our device showed the capability to sense blue light. Thus, we only extracted pixels of the blue channel for the recognition task. (c), The confusion matrix of the test results for 764 images in the CIFAR-10 dataset. The yellow-colored diagonal elements in the matrix represent the correctly identified cases.
Credit
by Kumar, D., Joharji, L., Li, H. et al.
Usage Restrictions
Credit must be given to the creator.
License
CC BY