The Cambrian Kuanchuanpu Formation in southern Shaanxi, China is a critical window for the understanding of the Cambrian explosion, because of abundant and various exceptionally preserved metazoans and embryo fossils ...The Cambrian Kuanchuanpu Formation in southern Shaanxi, China is a critical window for the understanding of the Cambrian explosion, because of abundant and various exceptionally preserved metazoans and embryo fossils yielded. The efficiency of traditional sample manually selecting with microscopes is quite low and hinder the discoveries of new species, thus recognition and classification of microfossils by artificial intelligence(AI) is substantially in the request. In this paper, we develop a procedure for fossil area segmentation in common multi-typed mixed photos by improved watershed algorithm. And for better fossil recognition, previous histogram of oriented grandient(HOG) algorithm is replaced by scale invariant feature transform(SIFT), which is feasible for the segmented images and increase the accuracy significantly. Thus, the scope of application of AI fossil recognition can be extended form single fossil image to multi-typed mixed images and the reliability is also secured, as the result of our test presents a high(at least 84%) accuracy of fossil recognition.展开更多
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences [No. XDB26000000]the Natural Science Foundation of China [Nos. 41621003, 41772010, 41572017, 41672009, 41720104002].
文摘The Cambrian Kuanchuanpu Formation in southern Shaanxi, China is a critical window for the understanding of the Cambrian explosion, because of abundant and various exceptionally preserved metazoans and embryo fossils yielded. The efficiency of traditional sample manually selecting with microscopes is quite low and hinder the discoveries of new species, thus recognition and classification of microfossils by artificial intelligence(AI) is substantially in the request. In this paper, we develop a procedure for fossil area segmentation in common multi-typed mixed photos by improved watershed algorithm. And for better fossil recognition, previous histogram of oriented grandient(HOG) algorithm is replaced by scale invariant feature transform(SIFT), which is feasible for the segmented images and increase the accuracy significantly. Thus, the scope of application of AI fossil recognition can be extended form single fossil image to multi-typed mixed images and the reliability is also secured, as the result of our test presents a high(at least 84%) accuracy of fossil recognition.
