Face-sketch learning with human sketch-drawing order enforcement
نویسندگان
چکیده
منابع مشابه
Generic Sketch-Based Retrieval Learned without Drawing a Single Sketch
We cast the sketch-based retrieval as edge-map matching. A shared convolutional network is trained to extract descriptors from edge maps and sketches, which are treated as a special case of edge maps. The network is fine-tuned solely from edge maps of landmark images. The training images are acquired in a fully unsupervised manner from 3D landmark models obtained by an automated structurefrom-m...
متن کاملSketch-Driven Orthogonal Graph Drawing
We present an orthogonal graph drawing algorithm that uses a sketchy drawing of the graph as input. While the algorithm produces an orthogonal drawing with few bends in the Kandinsky model it also preserves the general appearance of the sketch. Potential applications for this kind of drawing algorithm include the generation of schematic maps from geographic networks and interactive orthogonal g...
متن کاملFace Sketch-Photo Recognition
Automatic systems for matching facial sketch images from the police mug shot database are very important for law enforcement agencies. These systems can help to locate or narrow down potential suspects. In this work, we deal the problem of face recognition through forensic sketches with focus on the Eigentransformation method and Local feature-based discriminant analysis (LFDA). The Eigentrasfo...
متن کاملDrawing on the World: Sketch in Context
In this paper we introduce our approach to implementing context-rich sketch-based interfaces. By “contextrich” we mean interfaces for systems that refer to real-world objects. For example, a system that allowed the user to draw on an annotated video feed instead of a blank canvas would yield this kind of context-richness. We describe “Drawing on the World”, the concept that taking what is being...
متن کاملFace Sketch Synthesis and Recognition
In this paper, we propose a novel face photo retrieval system using sketch drawings. By transforming a photo image into a sketch, we reduce the difference between photo and sketch significantly, thus allow effective matching between the two. To improve the synthesis performance, we separate shape and texture information in a face photo, and conduct transformation on them respectively. Finally a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science China Information Sciences
سال: 2020
ISSN: 1674-733X,1869-1919
DOI: 10.1007/s11432-019-2890-8