Early diagnosis of rice disease is important because it poses a considerable threat to agricultural productivity as well as the global food security of the world. It is challenging to obtain more reliable outcomes based on the percentage of RGB value using image processing outcomes for rice disease detections and classifications in the agricultural field. Machine learning, especially with a Convolutional Neural Network (CNN), is a great tool to overcome this problem. But the utilization of deep learning techniques often necessitates high-performance computing devices, costly GPUs and extensive machine infrastructure. As a result, this significantly raises the overall expenses for users. Therefore, the demand for smaller CNN models becomes particularly pronounced, especially in embedded systems, robotics and mobile applications. These domains require real-time performance and minimal computational overhead, making smaller CNN models highly desirable due to their lower computational cost. This paper introduces a novel CNN architecture which is comparatively small in size and promising in performance to predict rice leaf disease with moderate accuracy and lower time complexity. The CNN network is trained with processed images. The image processing is performed using segmentation and k-means clustering to remove background and green parts of affected images. This technique proposes to detect rice disease of rice brown spot, rice bacterial blight and leaf smut with reliable outcomes in disease classifications. The model is trained using an augmented dataset of 2700 images (60% data) and validated with 1200 images of disease-affected samples to identify rice disease in agricultural fields. The model is tested with 630 images (14% data); testing accuracy is 97.9%. The model is exported into a mobile application to introduce the real-life application of the outcome of this work. The model accuracy is compared to others work associated with this type of problem. It is found that the performance of the model and the application are satisfactory compared to other works related to this work. The over-all accuracy is notable, showing the reliability and dependability of this model to classify rice leaf diseases.

A typical semi-supervised learning-based scheme is based on training a single model for labeled data. For unlabeled data, it uses the pseudo-labeling method to obtain labels. However, the samples during pseudo-labeling are often filtered using a probability threshold, which suffers from the challenge of effective threshold selection. In the case of a high probability threshold, correct samples may not be labeled, and in the case of a low threshold, samples can be wrongly labeled. This threshold issue degrades the overall performance of the model. This paper addresses this vital issue by proposing a novel approach of SSL named Binary-Classifiers-Enabled Filters for Semi-Supervised Learning (BSSL) for labeling the unlabeled data by using binary classifiers as data filters. That is, we train binary classifiers dedicated to each class. After training, we propose three methods for labeling the unlabeled data; cascading, non-cascading, and rank-based binary classifiers. Our extensive experiment shows rank-based binary classifiers are the best choice for labeling the data. Our approach eliminates threshold selection to improve the performance of the model. Comprehensive experiments are performed to demonstrate the effectiveness of our approach on a variety of domains, including image classification, text classification and audio classification, datasets including MNIST, fashion-MNIST, EuroSat, ESC10, Free Spoken Digit dataset, Audio Emotion recognition, reuter and mice protein dataset. Rank based binary classifiers (BSSL) approach achieves absolute performance of atleast 10% and 5% over supervised learning(SL) and SSL, respectively on audio datasets in different number of sample cases except RAVDESS dataset. Moreover, BSSL shows tremendous performance on image datasets specifically when number of samples is very small. Overall, BSSL outperformed the purely supervised learning approach and SSL pseudo-labeling approaches in different number of samples cases.

Data augmentation is an effective way to increase the diversity of existing training datasets that result in improved generalization ability of convolutional neural networks (CNNs). The augmentation effect is usually global for the existing methods i.e., a single augmentation effect is applied to the whole image, thus limiting the diversity of local characteristics in augmented images. Moreover, the global augmentation effect does not support the most fundamental behavior of CNNs i.e., they focus more on local features (local texture, tiny noise etc.) than global shapes. We refer to this behavior as local bias property. In this paper, we propose a new data augmentation method, called Local Augment (LA), which highly alters the local bias property so that it can generate significantly diverse augmented images and offers the network with a better augmentation effect. First, we select few local patches in an image, then apply different types of augmentation strategies to each local patch. This augmentation process collapses the global structure of the object but creates locally diversified samples, which helps the network to learn the local bias property in a more generalized way. As a result, it increases the generalizability and the prediction accuracy of the network. To verify the effectiveness of the proposed method, we perform comprehensive experiments on image classification with benchmark datasets, where the proposed method outperforms the sate-of-the-art data augmentation techniques on ImageNet and STL10 and shows competitive performance on CIFAR100.

Early rice disease detection is vital in preventing damage to agricultural product output and quantity in the agricultural field. Manual observations of rice diseases are tedious, costly, and time-consuming, especially when classifying disease patterns and color while dealing with non-native diseases. Hence, image processing and Machine Learning (ML) techniques are used to detect rice disease early and within a relatively brief time period. This article aims to demonstrate the performance of different ML algorithms in rice disease detection through image processing. We critically examined different techniques, and the outcomes of previous research have been reviewed to compare the performance of rice disease classifications. Performance has been evaluated based on the criteria of feature extraction, clustering, segmentation, noise reduction, and level of accuracy of disease detection techniques. This paper also showcases various algorithms for different datasets in terms of training methods, image preprocessing with clustering and filtering criteria, and testing with reliable outcomes. Through this review, we provide valuable insights into the current state of ML-based approaches for the early detection of rice diseases, and assist future research and improvement. In addition, we discuss several challenges that must be overcome in order to achieve effective identification of rice diseases.

Recently, discriminative learning based denoising methods have received much attention and have been studied to a large extent because of their high denoising performance with significantly shorter inference time compared to model based denoising methods. In this paper, we consider a perceptually motivated blind image denoising problem, that removes various levels of noise from an observed noisy image with a single model and produces visually pleasant images. It is well known that very few blind image denoising methods are available and they have shown limited quality of restored images because they sacrifice the fine image details during the denoising process due to over-smoothing, resulting in visually unpleasant images. To overcome these problems, we propose a novel loss function that encourages the network to restore noise free images by focusing on the perceived visual quality. Then, the proposed loss function is adopted to an encoder decoder network with skip connections that produces visually pleasant images with highly preserved fine image details. Further this method is robust and constantly performs well for several unknown noise levels. Our extensive experimental results show the superiority of the proposed method both quantitatively and qualitatively.

Deep neural networks (DNNs) for single image super-resolution (SISR) tend to have large model size and high computation complexity to achieve promising restoration performance. Unlike image classification, model compression for SISR has rarely been studied. In this paper, we found out that DNNs for image classification and SISR have often different characteristics in terms of layer importance. That is, contrary to the DNNs for image classification, the performance of SISR networks hardly decrease even if a few layers are eliminated during inference. This is due to the fact that they typically consist of a bunch of hierarchical and complex residual connections. Based on that key observation, we propose a layer-wise extreme network compression method for SISR. The proposed method consists of: i) reinforcement learning based joint framework for layer-wise quantization and pruning both of which are effectively incorporated into the search space; ii) a progressive preserve ratio scheduling that reflects importance in each layer more effectively, yielding much higher compression efficiency. Our comprehensive experiments show that the proposed method can effectively be applied to the existing SISR networks, thus extremely reducing the model size up to 97% (i.e., 1 bit per weight on average) with marginal performance degradation compared to the corresponding full-precision models.