公开(公告)号：US09501724B1

公开(公告)日：2016-11-22

申请号：US14734466

申请日：2015-06-09

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： Jianchao Yang ,  Zhangyang Wang ,  Jonathan Brandt ,  Hailin Jin ,  Elya Shechtman ,  Aseem Omprakash Agarwala

IPC: G06K9/00 ,  G06K9/36 ,  G06K9/66 ,  G06K9/62 ,  G06K9/68 ,  G06T3/40

CPC classification number: G06T3/40 ,  G06K9/6255 ,  G06K9/6828

Abstract: A convolutional neural network (CNN) is trained for font recognition and font similarity learning. In a training phase, text images with font labels are synthesized by introducing variances to minimize the gap between the training images and real-world text images. Training images are generated and input into the CNN. The output is fed into an N-way softmax function dependent on the number of fonts the CNN is being trained on, producing a distribution of classified text images over N class labels. In a testing phase, each test image is normalized in height and squeezed in aspect ratio resulting in a plurality of test patches. The CNN averages the probabilities of each test patch belonging to a set of fonts to obtain a classification. Feature representations may be extracted and utilized to define font similarity between fonts, which may be utilized in font suggestion, font browsing, or font recognition applications.

Abstract translation: 对卷积神经网络（CNN）进行字体识别和字体相似学习。 在训练阶段，通过引入差异来合成具有字体标签的文本图像，以最小化训练图像与真实世界文本图像之间的差距。 生成训练图像并将其输入到CNN中。 根据CNN正在训练的字体数量，输出被输入到N-way softmax函数中，产生N类标签上分类文本图像的分布。 在测试阶段，每个测试图像的高度被标准化，并以纵横比挤压，从而产生多个测试贴片。 CNN对属于一组字体的每个测试补丁的概率进行平均，以获得分类。 可以提取和利用特征表示来定义可以在字体建议，字体浏览或字体识别应用中使用的字体之间的字体相似性。