Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach
نویسندگان
چکیده
منابع مشابه
Free Hand-Drawn Sketch Segmentation
In this paper, we study the problem of how to segment a freehand sketch at the object level. By carefully considering the basic principles of human perceptual organization, a real-time solution is presented to automatically segment a user’s sketch during his/her drawing. First, a graph-based sketch segmentation algorithm is proposed to segment a cluttered sketch into multiple parts based on the...
متن کاملA complete hand-drawn sketch vectorization framework
Vectorizing hand-drawn sketches is a challenging task, which is of paramount importance for creating CAD vectorized versions for the fashion and creative workflows. This paper proposes a complete framework that automatically transforms noisy and complex hand-drawn sketches with different stroke types in a precise, reliable and highly-simplified vectorized model. The proposed framework includes ...
متن کاملFreehand Sketch Recognition Using Deep Features
Freehand sketches often contain sparse visual detail. In spite of the sparsity, they are easily and consistently recognized by humans across cultures, languages and age groups. Therefore, analyzing such sparse sketches can aid our understanding of the neurocognitive processes involved in visual representation and recognition. In the recent past, Convolutional Neural Networks (CNNs) have emerged...
متن کاملA novel hand-drawn sketch descriptor based on the fusion of multiple features
Constructing a distinctive and robust sketch descriptor is one of the most challenging problems in sketch based applications. In this paper, a new hand-drawn sketch descriptor is proposed. The proposed descriptor utilizes the statistic information of multiple features and bag-of-features representation to achieve translation and scale invariance and rotation robustness. The proposed descriptor ...
متن کاملLearning Deep Features via Congenerous Cosine Loss for Person Recognition
Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance. In this paper, we propose a novel method to address this task by training a network to obtain robust and representative features. A key observation is that traditional cross entropy loss only enforces the inter-class variation among samples and ignores to narrow down th...
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: International Journal of Advanced Computer Science and Applications
سال: 2019
ISSN: 2156-5570,2158-107X
DOI: 10.14569/ijacsa.2019.0100958