Coffee Flower Identification Using Binarization Algorithm Based on Convolutional Neural Network for Digital Images

Abstract

Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5° angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.

An Improved Method Research on Graphics and Image Processing System

“…For example, when processing criminal investigation photographs (including the extraction of concealed trail information and fisheye correction, among other things), the public security system will use foreign costly expert software. e fundamental problem is that domestic software is inadequate, while commercial software often falls short of the specifications [22]. e schedule is as follows: on the basis of continual modification, display written on the display of black-and-white pictures in computers has become a more sophisticated image editing tool and has been called Photoshop, presently, together with the marketing of commercial devices [23].…”

Progress in the Application of CNN-Based Image Classification and Recognition in Whole Crop Growth Cycles

“…Xu et al [96] utilized an improved Mask R-CNN model for instance segmentation to accurately segment cherry tomatoes. The combination of the Otsu binarization algorithm and CNN efficiently enabled the recognition of coffee flowers [97].…”

“…The performance of CNN models is heavily influenced by the number of sample images, and thus it is essential to increase the quantity of available samples. For complex agricultural scenes, achieving acceptable target-detection results often requires at least 3000 to 4000 marked samples per class [97]. However, among more than 200 related studies conducted between 2020 and 2023, the number of image samples exceeded 20,000 in less than 10% of the cases.…”

Intelligent Target Tracking of Unmanned Vehicles Considering Convolutional Neural Networks

“…In the tracking method using statistical matching, the position of the target in the picture is obtained first, and the state space such as the position and velocity of the target is modeled. The state prediction equation is as follows [7][8]:…”