{"title":"芯片封装轮廓图中多目标的自动分割方法","authors":"Lingfei Tang, Xiaoyu Liang, Lv Wu, N. Xu","doi":"10.1109/CACML55074.2022.00041","DOIUrl":null,"url":null,"abstract":"Chip package design is an important part of chip design automation, and chip package outline drawings are the basis for chip package design, which plays an important role. The automatic segmentation of the chip package outline drawing can improve the work efficiency of engineers. This paper proposes an effective technique for automatic segmentation of the chip package outline drawing, which realizes the segmentation and extraction of multiple objects in the chip package outline drawing. Mainly through image preprocessing, morphological processing, contour extraction, multi-objects segmentation and extraction four parts to achieve. The adaptive dilation method is proposed in the morphological processing, and the approximate circumscribed polygon method is proposed in the contour extraction, in the multi-objects segmentation part, a method of extracting objects according to irregular contour segmentation is proposed. The experimental results compared with other classical methods show that the method proposed in this paper works best. In the chip package outline drawing samples including 346 objects to be segmented, the method achieves a segmentation accuracy of 86.99% demonstrating the effectiveness of the proposed technique.","PeriodicalId":137505,"journal":{"name":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic Segmentation Method of Multiple Objects in Chip Package Outline Drawings\",\"authors\":\"Lingfei Tang, Xiaoyu Liang, Lv Wu, N. Xu\",\"doi\":\"10.1109/CACML55074.2022.00041\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Chip package design is an important part of chip design automation, and chip package outline drawings are the basis for chip package design, which plays an important role. The automatic segmentation of the chip package outline drawing can improve the work efficiency of engineers. This paper proposes an effective technique for automatic segmentation of the chip package outline drawing, which realizes the segmentation and extraction of multiple objects in the chip package outline drawing. Mainly through image preprocessing, morphological processing, contour extraction, multi-objects segmentation and extraction four parts to achieve. The adaptive dilation method is proposed in the morphological processing, and the approximate circumscribed polygon method is proposed in the contour extraction, in the multi-objects segmentation part, a method of extracting objects according to irregular contour segmentation is proposed. The experimental results compared with other classical methods show that the method proposed in this paper works best. In the chip package outline drawing samples including 346 objects to be segmented, the method achieves a segmentation accuracy of 86.99% demonstrating the effectiveness of the proposed technique.\",\"PeriodicalId\":137505,\"journal\":{\"name\":\"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)\",\"volume\":\"54 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CACML55074.2022.00041\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 Asia Conference on Algorithms, Computing and Machine Learning (CACML)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CACML55074.2022.00041","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Automatic Segmentation Method of Multiple Objects in Chip Package Outline Drawings
Chip package design is an important part of chip design automation, and chip package outline drawings are the basis for chip package design, which plays an important role. The automatic segmentation of the chip package outline drawing can improve the work efficiency of engineers. This paper proposes an effective technique for automatic segmentation of the chip package outline drawing, which realizes the segmentation and extraction of multiple objects in the chip package outline drawing. Mainly through image preprocessing, morphological processing, contour extraction, multi-objects segmentation and extraction four parts to achieve. The adaptive dilation method is proposed in the morphological processing, and the approximate circumscribed polygon method is proposed in the contour extraction, in the multi-objects segmentation part, a method of extracting objects according to irregular contour segmentation is proposed. The experimental results compared with other classical methods show that the method proposed in this paper works best. In the chip package outline drawing samples including 346 objects to be segmented, the method achieves a segmentation accuracy of 86.99% demonstrating the effectiveness of the proposed technique.