Beans Leaf Diseases Classification Using MobileNet Models

Abstract

In recent years, plant leaf diseases has become a widespread problem for which an accurate research and rapid application of deep learning in plant disease classification is required. Beans is also one of the most important plants and seeds which are used worldwide for cooking in either dried or fresh form. Beans are a great source of protein that offer many health benefits, but there are a lot of diseases associated with beans leaf which hinder its production such as angular leaf spot disease and bean rust disease. Thus, an accurate classification of bean leaf diseases is needed to solve the problem in the early stage. A deep learning approach is proposed to identify and classify beans leaf disease by using public dataset of leaf image and MobileNet model with the open source library TensorFlow. In this study, we proposed a method to classify beans leaf disease and to find and describe the efficient network architecture (hyperparameters and optimization methods ). Moreover, after applying each architecture separately, we compared their obtained results to find out the best architecture configuration for classifying bean leaf diseases and their results. On the other hand, to satisfy the classification requirements, the model was trained using MobileNetV2 architecture under the some controlled conditions as MobileNet to check if we could get faster training times, higher accuracy and easier retraining, we evaluated and implemented MobileNet architectures on one public dataset including two unhealthy classes (angular leaf spot disease and bean rust disease) and one healthy class, the algorithm was tested on 1296 images of bean leaf, the obtained results showed that our MobileNet model achieves highest classification performance for beans leaf disease, the classification average accuracy of the proposed model is more than 97% on training dataset and more than 92% on test data for two unhealthy classes and one healthy class.

ECDBMFA: Design of an Ensemble engine for Crop Disease detection via Bioinspired Multidomain Feature Analysis

“…This accuracy is improved due to use of BFO process, which assists in identification of high-density feature sets, that have lower redundancies. Similarly, the precision levels for crop disease identification can be observed from table 3 MNet [8] SPED CNN [6] As per this extensive evaluation and its visualization in figure 4, it can be observed that the proposed model is able to improve classification precision levels by 18.3% when compared in SPED CNN [6], 9.4% when compared with MNet [8], and 8.5% when compared with FR CNN [9], which makes it highly useful for an extensive set of consistencyaware classification scenarios. This precision is improved due to use of ensemble classification process, which assists in identification of optimal classes for different disease types.…”

“…As per this extensive evaluation and its visualization in figure 3, it can be observed that the proposed model is able to improve classification accuracy levels by 16.5% when compared in SPED CNN [6], 5.9% when compared with MNet [8], and 4.1% when compared with FR CNN [9], which makes it highly useful for a wide variety of classification scenarios. This accuracy is improved due to use of BFO process, which assists in identification of high-density feature sets, that have lower redundancies.…”

“…The RoIs are represented via a multidomain feature extraction process that combines frequency, convolutional, Gabor, wavelet and entropy components. [6], MNet [8], and FR CNN [9] FR CNN [9] ECD BM FA…”

“…Both the Plant Village dataset, which contains 55,448 images, and the expanded dataset, which has 61,486 images, were used to train the model. In the studies proposed in [8,9,10,11,12,13 [14,15,16,17,18] categorized numerous leaf diseases (SSD). Images of diseases seen on the leaves of commercially produced banana, sugarcane, cotton, potato, brinjal, carrot, Chile, rice, and wheat are included in this collection.…”

A Novel Enhanced VGG16 Model to Tackle Grapevine Leaves Diseases With Automatic Method

“…Elfatimi et al [61] presented a method to classify beans leaf disease. The model was trained using MobileNetV2 architecture under some controlled conditions as MobileNet.…”