No abstract

IntroductionCurrent detection methods for apple leaf diseases still suffer some challenges, such as the high number of parameters, low detection speed and poor detection performance for small dense spots, which limit the practical applications in agriculture. Therefore, an efficient and accurate model for apple leaf disease detection based on YOLOv5 is proposed and named EADD-YOLO.MethodsIn the EADD-YOLO, the lightweight shufflenet inverted residual module is utilized to reconstruct the backbone network, and an efficient feature learning module designed through depthwise convolution is proposed and introduced to the neck network. The aim is to reduce the number of parameters and floating point of operations (FLOPs) during feature extraction and feature fusion, thus increasing the operational efficiency of the network with less impact on detection performance. In addition, the coordinate attention module is embedded into the critical locations of the network to select the critical spot information and suppress useless information, which is to enhance the detection accuracy of diseases with various sizes from different scenes. Furthermore, the SIoU loss replaces CIoU loss as the bounding box regression loss function to improve the accuracy of prediction box localization.ResultsThe experimental results indicate that the proposed method can achieve the detection performance of 95.5% on the mean average precision and a speed of 625 frames per second (FPS) on the apple leaf disease dataset (ALDD). Compared to the latest research method on the ALDD, the detection accuracy and speed of the proposed method were improved by 12.3% and 596 FPS, respectively. In addition, the parameter quantity and FLOPs of the proposed method were much less than other relevant popular algorithms.DiscussionIn summary, the proposed method not only has a satisfactory detection effect, but also has fewer parameters and high calculation efficiency compared with the existing approaches. Therefore, the proposed method provides a high-performance solution for the early diagnosis of apple leaf disease and can be applied in agricultural robots. The code repository is open-sourced at https://github.com/AWANWY/EADD-YOLO.

As a low-level feature in content-based image retrieval (CBIR), color histogram does not take into account the spatial correlation of the same or similar valued elements. In order to overcome this drawback, color approximation histogram based on rough sets theory is proposed in this paper. The image is partitioned into a collection of non-overlapping windows (called granule G). According to the pixels color in granule, color lower approximation histogram and color boundary histogram are denoted as low level feature in CBIR. Experiment results show that the precision and recall rate of color approximation histogram as low-level feature are higher than that of color histogram as low-level feature. The color approximation histogram classifies the granule into color lower approximation set or color boundary set, so it overcomes the drawback of color histogram as low-level feature. Keywords-Rough set theory; CBIR; Color quantization; Color approximation histogram I. INTRODUCITONWith the development of computer vision technology and the increase in the number of images taken by digital video devices, searching for images containing user-specified characteristics in large image databases has become more and more important and challenging than ever before. Image retrieval systems attempt to search through a database to find images that are perceptually similar to a query image. There are two frameworks: text-based and content-based. Text-based image retrieval is based on one or more keywords specified by the user to search image. However, there are cases in which a query request cannot be easily described by keywords. To overcome the above disadvantages in text-based retrieval system, content-based image retrieval (CBIR) was introduced in the early 1980s [1].In CBIR, images are indexed by their visual content, such as color, texture, shapes and color layout (both color features and spatial relations). The features are stored in an image feature database for future use. When a query image is given, the features of the query image are extracted to match the features in the feature database by a pre-established algorithm, so that a group of similar images to the query image can be returned as the retrieval images.Color feature is one of the most widely used features in image retrieval. Colors are defined on a selected color space such as RGB, LAB, LUV, HSV (HSL), YCrCb and the huemin-max-difference (HMMD). Common color features or descriptors in CBIR systems include color-covariance matrix, color histogram, color moments, and color coherence vectorAs a content feature, a color spectrum or histogram is a simple and efficient low-level feature. However, if calculated directly in a triple-dimension color space (e.g., RGB), both the storage space and computing time will be very high. So color quantization is necessary before extraction of the image color features.In [3], quantized color histogram in HSV color space is selected as the feature to search image. The advantage of such method is that they do not need any prior inform...

Based on the basic principles of actuarial, with the latest provisions of pension system reform of china, using the individual cost method, implicit pension debt of China in 2009 can be calculated with the model.