Accurately and effectively detecting the growth position and contour size of apple fruits is crucial for achieving intelligent picking and yield predictions. Thus, an effective fruit edge detection algorithm is necessary. In this study, a fusion edge detection model (RED) based on a convolutional neural network and rough sets was proposed. The Faster-RCNN was used to segment multiple apple images into a single apple image for edge detection, greatly reducing the surrounding noise of the target. Moreover, the K-means clustering algorithm was used to segment the target of a single apple image for further noise reduction. Considering the influence of illumination, complex backgrounds and dense occlusions, rough set was applied to obtain the edge image of the target for the upper and lower approximation images, and the results were compared with those of relevant algorithms in this field. The experimental results showed that the RED model in this paper had high accuracy and robustness, and its detection accuracy and stability were significantly improved compared to those of traditional operators, especially under the influence of illumination and complex backgrounds. The RED model is expected to provide a promising basis for intelligent fruit picking and yield prediction.

Most existing arbitrary shape text detection methods employ connected components and text center lines for grouping text instances, which assume that texts in adjacent positions belong to the same instance. However, many hard-to-group scene texts are too complex to be effectively processed in this way. To address this challenge, we propose a novel scene text-spotting method that utilizes feature-based clustering inspired by human cognitive principles of text perception. Our approach involves first utilizing a character spotter to obtain the location and the transcription information of the characters. Then, a lightweight recognition network extracts the visual features of the characters by their locations. These visual features are then grouped into instances through a K-means-fuzzy-net, which explicitly model visual feature similarity to effectively group the nested text, the large-margin text, the continuous text, and the one with overlapping characters. Finally, the recognition results of text instances are processed by a word correction module to improve the overall accuracy and reduce the vulnerability of individual character detection. Additionally, we have contributed a hard-to-group text dataset. Experiments demonstrate the state-of-the-art performance of our method in addressing scenarios. Hard-to-group text dataset is available at: https://github.com/baggio321/Hard-to-Group-Text-Dataset.