Detecting cassava mosaic disease using a deep residual convolutional neural network with distinct block processing

For people in developing countries, cassava is a major source of calories and carbohydrates. However, Cassava Mosaic Disease (CMD) has become a major cause of concern among farmers in sub-Saharan Africa countries, which rely on cassava for both business and local consumption. The article proposes a novel deep residual convolution neural network (DRNN) for CMD detection in cassava leaf images. With the aid of distinct block processing, we can counterbalance the imbalanced image dataset of the cassava diseases and increase the number of images available for training and testing. Moreover, we adjust low contrast using Gamma correction and decorrelation stretching to enhance the color separation of an image with significant band-to-band correlation. Experimental results demonstrate that using a balanced dataset of images increases the accuracy of classification. The proposed DRNN model outperforms the plain convolutional neural network (PCNN) by a significant margin of 9.25% on the Cassava Disease Dataset from Kaggle.

Self-Adaptive Image Reconstruction Inspired by Insect Compound Eye Mechanism

Inspired by the mechanism of imaging and adaptation to luminosity in insect compound eyes (ICE), we propose an ICE-based adaptive reconstruction method (ARM-ICE), which can adjust the sampling vision field of image according to the environment light intensity. The target scene can be compressive, sampled independently with multichannel through ARM-ICE. Meanwhile, ARM-ICE can regulate the visual field of sampling to control imaging according to the environment light intensity. Based on the compressed sensing joint sparse model (JSM-1), we establish an information processing system of ARM-ICE. The simulation of a four-channel ARM-ICE system shows that the new method improves the peak signal-to-noise ratio (PSNR) and resolution of the reconstructed target scene under two different cases of light intensity. Furthermore, there is no distinct block effect in the result, and the edge of the reconstructed image is smoother than that obtained by the other two reconstruction methods in this work.

Hemispheric Refractoriness and Control of Reaction Time

Experiments are described which attempt to assess the relative efficiency of the hemispheres and their relationship in performance on complex RT tasks. A divided visual field method was used to direct signals to the temporal or nasal retinae of each eye thus passing information to separate hemispheres. A comparison of the separate response times was used to assess the relative efficiency of each hemisphere but significant differences were not observed. This suggests that each may be the equal of the other in organizing simple responses. A method was used to examine more complex RT by presenting the subject with two simultaneous signals for response. When pairs of signals are directed to separate hemispheres, response times are at their lowest value. When signals are directed to separate hemispheres through the same eye, a significant increase in RT occurs. A source of mutual interference appears to exist at the level of the eye. Response times are extended to their greatest value, however, when both signals are directed to the same hemisphere. This block to function has been described as “hemispheric refractoriness”, and is different for the two hemispheres. While each show a distinct block to function the extent of this is greater in the right or minor hemisphere than it is in the left or major hemisphere.