Object Recognition via Local Patch Labelling

In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of this problem is to be able to recognize any member of a category of objects in spite of wide variations in visual appearance due to variations in the form and colour of the object, occlusions, geometrical transformations (such as scaling and rotation), changes in illumination, and potentially non-rigid deformations of the object itself. In this paper we focus on the detection of objects within images by combining information from a large number of small regions, or 'patches', of the image. Since detailed hand-segmentation and labelling of images is very labour intensive, we make use of 'weakly labelled' data in which the training images are labelled only according to the presence or absence of each category of object. A major challenge presented by this problem is that the foreground object is accompanied by widely varying background clutter, and the system must learn to distinguish the foreground from the background without the aid of labelled data. In this paper we first show that patches which are highly relevant for the object discrimination problem can be selected automatically from a large dictionary of candidate patches during learning, and that this leads to improved classification compared to direct use of the full dictionary. We then explore alternative techniques which are able to provide labels for the individual patches, as well as for the image as a whole, so that each patch is identified as belonging to one of the object categories or to the background class. This provides a rough indication of the location of the object or objects within the image. Again these individual patch labels must be learned on the basis only of overall image class labels. We develop two such approaches, one discriminative and one generative, and compare their performance both in terms of patch labelling and image labelling. Our results show that good classification performance can be obtained on challenging data sets using only weak training labels, and they also highlight some of the relative merits of discriminative and generative approaches.
Deterministic and Statistical Methods in Machine LearningVolume 3635 of the series Lecture Notes in Computer Science


A generative model for multi class object recognition and detection
Ulusoy, İlkay (2006-01-01)
In this study, a generative type probabilistic model is proposed for object recognition. This model is trained by weakly labelled images and performs classification and detection at the same time. When test on highly challenging data sets, the model performs good for both tasks (classification and detection).
Comparison of generative and discriminative techniques for object detection and classification
Ulusoy, İlkay (2004-01-01)
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use thes...
Camera motion blur and its effect on feature detectors
Üzer, Ferit; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2010)
Perception, hence the usage of visual sensors is indispensable in mobile and autonomous robotics. Visual sensors such as cameras, rigidly mounted on a robot frame are the most common usage scenario. In this case, the motion of the camera due to the motion of the moving platform as well as the resulting shocks or vibrations causes a number of distortions on video frame sequences. Two most important ones are the frame-to-frame changes of the line-of-sight (LOS) and the presence of motion blur in individual fr...
Object Segmentation in Multi-view Video via Color, Depth and Motion Cues
Cigla, Cevahir; Alatan, Abdullah Aydın (2009-01-01)
In the light of dense depth map estimation, motion estimation and object segmentation, the research on multi-view video (MVV) content has becoming increasingly popular due to its wide application areas in the near future. In this work, object segmentation problem is studied by additional cues due to depth and motion fields. Segmentation is achieved by modeling images as graphical models and performing popular Normalized Cuts method with some modifications. In the graphical models, each node is represented b...
Object recognition and segmentation via shape models
Altınoklu, Metin Burak; Ulusoy, İlkay; Tarı, Zehra Sibel; Department of Electrical and Electronics Engineering (2016)
In this thesis, the problem of object detection, recognition and segmentation in computer vision is addressed with shape based methods. An efficient object detection method based on a sparse skeleton has been proposed. The proposed method is an improved chamfer template matching method for recognition of articulated objects. Using a probabilistic graphical model structure, shape variation is represented in a skeletal shape model, where nodes correspond to parts consisting of lines and edges correspond to pa...
Citation Formats
İ. Ulusoy, “Object Recognition via Local Patch Labelling,” Deterministic and Statistical Methods in Machine LearningVolume 3635 of the series Lecture Notes in Computer Science, pp. 1–21, 2005, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/42602.