Abstract: A method for retrieving footprint images is provided, comprising: pre-training models; cleaning footprint data and conducting expansion pre-processing by using the pre-trained models, dividing the footprint data into multiple data sets; adjusting full connection layers and classification layers of the models; training the models again by using the data sets through the parameters of the pre-trained models; saving the models trained twice, removing the classification layer, executing a feature extraction for images in an image library and a retrieval library to form a feature index library; connecting the features extracted by three models to form fused features, establishing a fused feature vector index library; extracting the features of the images in the image library to be retrieved in advance, and establishing a feature vector library; calculating distances in the retrieval library and the image library when a single footprint image is inputted, thereby outputting the image with the highest similarity.

Abstract: An electronic device substrate, a manufacturing method and a display device are provided. The electronic device substrate includes a base substrate, an organic encapsulation layer and a padding structure. The organic encapsulation layer is on the base substrate and includes a main part and an edge part; the padding structure on the base substrate protrudes from the base substrate; the edge part of the organic encapsulation layer at least partially covers the padding structure; with respect to the base substrate, a height of a part that is included by the padding structure and is away from the main part of the organic encapsulation layer is greater than a height of another part that is included by the padding structure and is close to the main part of the organic encapsulation layer.

Abstract: A method for retrieving footprint images is provided, comprising: pre-training models; cleaning footprint data and conducting expansion pre-processing by using the pre-trained models, dividing the footprint data into multiple data sets; adjusting full connection layers and classification layers of the models; training the models again by using the data sets through the parameters of the pre-trained models; saving the models trained twice, removing the classification layer, executing a feature extraction for images in an image library and a retrieval library to form a feature index library; connecting the features extracted by three models to form fused features, establishing a fused feature vector index library; extracting the features of the images in the image library to be retrieved in advance, and establishing a feature vector library; calculating distances in the retrieval library and the image library when a single footprint image is inputted, thereby outputting the image with the highest similarity.

Abstract: An electronic device substrate, a manufacturing method and a display device are provided. The electronic device substrate includes a base substrate, an organic encapsulation layer and a padding structure. The organic encapsulation layer is on the base substrate and includes a main part and an edge part; the padding structure on the base substrate protrudes from the base substrate; the edge part of the organic encapsulation layer at least partially covers the padding structure; with respect to the base substrate, a height of a part that is included by the padding structure and is away from the main part of the organic encapsulation layer is greater than a height of another part that is included by the padding structure and is close to the main part of the organic encapsulation layer.