Clustering appearance and shape by learning jigsaws
نویسندگان
چکیده
Patch-based appearance models are used in a wide range of computer vision applications. To learn such models it has previously been necessary to specify a suitable set of patch sizes and shapes by hand. In the jigsaw model presented here, the shape, size and appearance of patches are learned automatically from the repeated structures in a set of training images. By learning such irregularly shaped ‘jigsaw pieces’, we are able to discover both the shape and the appearance of object parts without supervision. When applied to face images, for example, the learned jigsaw pieces are surprisingly strongly associated with face parts of different shapes and scales such as eyes, noses, eyebrows and cheeks, to name a few. We conclude that learning the shape of the patch not only improves the accuracy of appearance-based part detection but also allows for shape-based part detection. This enables parts of similar appearance but different shapes to be distinguished; for example, while foreheads and cheeks are both skin colored, they have markedly different shapes.
منابع مشابه
Learning Shape Models from Examples
This paper addresses the problem of learning shape models from examples. The contributions are twofold. First, a comparative study is performed of various methods for establishing shape correspondence based on shape decomposition, feature selection and alignment. Various registration methods using polygonal and Fourier features are extended to deal with shapes at multiple scales and the importa...
متن کاملFirst Year Report Learning Class-Specific Segmentation
This report details the work undertaken this year towards class-specific segmentation. The aim is to take an image known to contain an object of a particular class, and return for each pixel a figure-ground segmentation value. A training corpus consisting of images and their ground-truth segmentation masks is used to learn shape and appearance models. Our shape model consists of local shape pat...
متن کاملA Comparative Study of Some Clustering Algorithms on Shape Data
Recently, some statistical studies have been done using the shape data. One of these studies is clustering shape data, which is the main topic of this paper. We are going to study some clustering algorithms on shape data and then introduce the best algorithm based on accuracy, speed, and scalability criteria. In addition, we propose a method for representing the shape data that facilitates and ...
متن کاملHigh-Dimensional Unsupervised Active Learning Method
In this work, a hierarchical ensemble of projected clustering algorithm for high-dimensional data is proposed. The basic concept of the algorithm is based on the active learning method (ALM) which is a fuzzy learning scheme, inspired by some behavioral features of human brain functionality. High-dimensional unsupervised active learning method (HUALM) is a clustering algorithm which blurs the da...
متن کاملSEDAI et al.: LOCALIZED FUSION OF FEATURES FOR 3D HUMAN POSE ESTIMATION 1 Localized fusion of Shape and Appearance features for 3D Human Pose Estimation
This paper presents a learning-based method for combining the shape and appearance feature types for 3D human pose estimation from single-view images. Our method is based on clustering the 3D pose space into several modular regions and learning the regressors for both feature types and their optimal fusion scenario in each region. This way the complementary information of the individual feature...
متن کامل