Diagnosis of Citrus Greening Using Artificial Intelligence: A Faster Region-Based Convolutional Neural Network Approach with Convolution Block Attention Module-Integrated VGGNet and ResNet Models.

The vector-transmitted Citrus Greening (CG) disease, also called Huanglongbing, is one of the most destructive diseases of citrus. Since no measures for directly controlling this disease are available at present, current disease management integrates several measures, such as vector control, the use of disease-free trees, the removal of diseased trees, etc. The most essential issue in integrated management is how CG-infected trees can be detected efficiently. For CG detection, digital image analyses using deep learning algorithms have attracted much interest from both researchers and growers. Models using transfer learning with the Faster R-CNN architecture were constructed and compared with two pre-trained Convolutional Neural Network (CNN) models, VGGNet and ResNet. Their efficiency was examined by integrating their feature extraction capabilities into the Convolution Block Attention Module (CBAM) to create VGGNet+CBAM and ResNet+CBAM variants. ResNet models performed best. Moreover, the integration of CBAM notably improved CG disease detection precision and the overall performance of the models. Efficient models with transfer learning using Faster R-CNN were loaded on web applications to facilitate access for real-time diagnosis by farmers via the deployment of in-field images. The practical ability of the applications to detect CG disease is discussed.

An investigation of surface reconstruction from binocular disparity based on standard regularization theory: comparison between "membrane" and "thin-plate" potential energy models.

Visible surfaces of three-dimensional objects are reconstructed from two-dimensional retinal images in the early stages of human visual processing. In the computational model of surface reconstruction based on the standard regularization theory, an energy function is minimized. Two types of model have been proposed, called "membrane" and "thin-plate" after their function formulas, in which the first or the second derivative of depth information is used. In this study, the threshold of surface reconstruction from binocular disparity was investigated using a sparse random dot stereogram, and the predictive accuracy of these models was evaluated. It was found that the thin-plate model reconstructed surfaces more accurately than the membrane model and showed good agreement with experimental results. The likelihood that these models imitate human processing of visual information is discussed in terms of the size of receptive fields in the visual pathways of the human cortex.

An fMRI study of the reverse perspective illusion.

"Reverse perspective" is a powerful visual illusion similar to the hollow mask illusion, but more interesting in producing the perception of an illusory motion in a stationary picture. It is caused by conflict between motion parallax and pictorial depth cues in 3D "relief" paintings built with depth inversion. Here we report the measurement of brain activation using fMRI in response to a reverse perspective (RP) object, as well as a normal perspective, 3D-relief object ("shadow-box", SB) and a 2D painting of the same architectural scene. The stimuli were presented to 10 subjects in static and rotating conditions, subtraction of which revealed strong activation of area MT in all three cases. Contrasts between the RP, SB and 2D conditions showed the strongest activation for RP and almost no difference between SB and 2D. The similarity of brain activation between SB and 2D stimuli was interpreted as indicating that observers perceive the illusion of realistic 3D depth in 2D pictures as entirely normal and not qualitatively different from the 3D structure of the shadow-box stimulus. Contrasts between the RP stimulus and either the SB or the 2D stimulus revealed activation of Brodmann Areas 7, 19 and MT (and cerebellar cortex), suggesting the usage of brain regions involved in mental rotation and depth perception in response to the reverse perspective illusion.

Effects of visual-field inversions on the reverse-perspective illusion.

The 'reverse-perspective' illusion entails the apparent motion of a stationary scene painted in relief and containing misleading depth cues. We have found that, using prism goggles to induce horizontal or vertical visual-field reversals, the illusory motion is greatly reduced or eliminated in the direction for which the goggles reverse the visual field. We argue that the illusion is a consequence of the observer's inability to reconcile changes in visual information due to body movement with implicit knowledge concerning anticipated changes. As such, the reverse-perspective illusion may prove to be useful in the study of the integration of linear perspective and motion parallax information.