Object Class Recognition Using Multiple Instance Learning with Image as a Bag of Subimages
ثبت نشده
چکیده
Object class recognition in a given image is a difficult problem. To classify a test image as hit or match for a particular object class requires the abstraction of an object, developed using real world images. This is where the difficulty lies since the images of an object class can have large-scale variations in terms of illumination, angle of view, scale, rotation, color, location, type etc (intra-class variations). For example, the different photographs of the object class ‘car’ from PASCAL VOC 2007 [1] dataset shown below differ from each other in aspects mentioned previously.
منابع مشابه
بازیابی تعاملی تصاویر طبیعت با بهره گیری از یادگیری چند نمونه ای
Content-based image retrieval (CBIR) has received considerable research interest in the recent years. The basic problem in CBIR is the semantic gap between the high-level image semantics and the low-level image features. Region-based image retrieval and learning from user interaction through relevance feedback are two main approaches to solving this problem. Recently, the research in integra...
متن کاملMultiple Instance Learning for Visual Recognition: Learning Latent Probabilistic Models
Many visual recognition tasks can be represented as multiple instance problems. Two examples are image categorization and video classification, where the instances are the image segments and video frames, respectively. In this regard, detecting and counting the instances of interest can help to improve recognition in a variety of applications. For example, classifying the collective activity of...
متن کاملMultiple-instance learning as a classifier combining problem
In multiple-instance learning (MIL), an object is represented as a bag consisting of a set of feature vectors called instances. In the training set, the labels of bags are given, while the uncertainty comes from the unknown labels of instances in the bags. In this paper, we study MIL with the assumption that instances are drawn from a mixture distribution of the concept and the non-concept, whi...
متن کاملImproving Image Categorization by Using Multiple Instance Learning with Spatial Relation
Image categorization is a challenging problem when a label is provided for the entire training image only instead of the object region. To eliminate labeling ambiguity, image categorization and object localization should be performed simultaneously. Discriminative Multiple Instance Learning (MIL) can be used for this task by regarding each image as a bag and sub-windows in the image as instance...
متن کاملClassification d'images et localisation d'objets par des méthodes de type noyau de Fisher. (Fisher kernel based models for image classification and object localization)
In this dissertation, we propose models and methods targeting image understanding tasks. In particular, we focus on Fisher kernel based approaches for the image classification and object localization problems. We group our studies into the following three main chapters. First, we propose novel image descriptors based on non-i.i.d. image models. Our starting point is the observation that local i...
متن کامل