The existing YOLOv5s object detection model has issues of missing small targets and lower detection accuracy in complex scenes. Therefore, YOLOv5s needs to be optimized based on these problems. Firstly, the coordinate attention mechanism and the structure based on receptive field Block are introduced to improve the accuracy of the model. Secondly, the coordinate attention mechanism and the omni-dimensional dynamic convolutional structure are introduced to improve the situation of missing small targets. Selected part of the data in PASCAL VOC2007 for experiments, and the final results show that the model in this paper improves the recall by 1.7%, the average precision mAP50 by 2%, and the average precision mAP50-95 by 3% compared to the yolov5s model. The model in this paper improves the detection accuracy to a certain extent and improves the leakage detection of important targets and is tested in industrial scenarios with good results.
For ancient paintings and calligraphies, including thangkas and murals, which are often of large format and cannot be scanned at one time, it is necessary to utilize high-precision CIS image sensors to scan the paintings and calligraphies several times in segments, and then finally get the finished images through image stitching. Among them, fast and accurate stitching of large format images with hundreds of millions of pixels is a major difficulty. Due to the huge size, more computational resources are required, and conventional image stitching algorithms can not directly complete the stitching task in the case of limited performance. Therefore, we propose a high-resolution image stitching algorithm OR-SIFT based on deep learning prediction of overlapping regions, which combines the convolutional neural network with the traditional feature detection method. It uses the neural network to predict the overlapping region as the region of interest for subsequent stitching algorithms. Then, an improved SIFT algorithm is used to extract and describe features in the overlapping region, followed by precise stitching. Additionally, a strategy for continuously stitching multiple high-resolution images is proposed to reduce computational complexity while ensuring accuracy, achieving continuous stitching of multiple high-resolution images.
KEYWORDS: Error control coding, Error analysis, Optical character recognition, Statistical modeling, Data modeling, Image processing, Target recognition, Semantics, Model-based design, Education and training
With the wide application of text recognition technology, the text recognition model's own limitations and environmental factors interfere with the recognition error rate is high. To address the above situation, a text error correction method based on MacBERT4CSC after text recognition is proposed. Firstly, using the single-word text recognition confidence, we obtain the suspected wrong words and positions by setting thresholds for error detection of the text to be corrected, and then iterate through the constructed confusion set for text error correction in priority, and after the traversal is completed, the MacBERT4CSC model recalls the candidate words with suspected wrong positions, and finally, after the similarity of the word code and the MacBERT4CSC model score meet the set conditions, The error correction is finally completed by sorting the candidate words that meet the conditions. By imitating the error type of word recognition to build the dataset for word recognition and calling Ali's word recognition API for word recognition to obtain the test set to be corrected, the comparison experiments show that the MacBERT4CSC recall and word bar code sorting method improves in accuracy, recall rate and F1 value compared with other deep models and traditional rule error correction methods, which verifies the effectiveness of the method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.