Méthode de Viola et Jones | EPFL Graph Search

thumb|alt=Un exemple de détection de visage par la méthode de Viola et Jones, les 7 visages présents sur l'image sont correctement détectés, sans fausses alarmes.|Un exemple de détection de visage par la méthode de Viola et Jones. La méthode de Viola et Jones est une méthode de détection d'objet dans une , proposée par les chercheurs Paul Viola et Michael Jones en 2001. Elle fait partie des toutes premières méthodes capables de détecter efficacement et en temps réel des objets dans une image. Inventée à l'origine pour détecter des visages, elle peut également être utilisée pour détecter d'autres types d'objets comme des voitures ou des avions. La méthode de Viola et Jones a été l'une des méthodes les plus connues et les plus utilisées, en particulier pour la détection de visages et la détection de personnes. En tant que procédé d'apprentissage supervisé, la méthode de Viola et Jones nécessite de quelques centaines à plusieurs milliers d'exemples de l'objet que l'on souhaite détecter

Sentiment Classification of Tweets using Hierarchical Classification

Afroze Ibrahim Baqapuri

This paper addresses the problem of sentiment classification of short messages on microblogging platforms. We apply machine learning and pattern recognition techniques to design and implement a classification system for microblog messages assigning them into one of three classes: positive, negative or neutral. As part of this work, we contributed a dataset consisting of approximately 10, 000 tweets, each labeled on a five point sentiment scale by three different people. Experiments demonstrate a detection rate between approximately 70% and an average false alarm rate of approximately 18% across all three classes. The developed classifier has been made available for online use.

Ieee2016

Multimodal person recognition in audio-visual streams

Do Hoang Nam Le

Multimedia databases are growing rapidly in size in the digital age. To increase the value of these data and to enhance the user experience, there is a need to make these videos searchable through automatic indexing. Because people appearing and talking in the videos are often of high interest for end users, indices that represent the location and identity of people in the archive are indispensable for video search and browsing tools. On the other hand, multimedia videos contain resourceful data of people in both visual and auditory domains. This offers a potential for multimodal learning in the task of human identification. Hence, the main theme of this thesis is on algorithms to create indexes and exploit the audio-visual correspondence in large multimedia corpuses based on person identities. First, this thesis deals with algorithms to create indexes through person discovery in videos. It involves several components: face and speaker diarization, face-voice association, and person naming. To obtain face clusters, we propose a novel face tracking approach that leverages face detectors with a tracking-by-detection framework relying on long term time-interval sensitive association costs. We use also shot context to further accelerate and improve face clustering. Face clusters are then associated to speaker clusters using dubbing and talking detection, in which a multimodal framework is introduced to represent the temporal relationship between the auditory and visual streams. We also improve speaker embeddings for recognition and clustering by using a regularizer called intra-class loss. In the second half, the thesis focuses on multimodal learning with face-voice data. Here, we aim to answer two research questions. First, can one improve a voice embedding using knowledge transferred from a face representation? We investigate several transfer learning approaches to constrain the target voice embedding space to share latent attributes with the source face embedding space. The crossmodal constrains act as regularizers helping voice models, especially in the low-data setting. The second question is can face clusters be used as training labels to learn a speaker embedding? To answer this, we explore the tolerance of embedding losses under label uncertainty. From the risk minimization perspective, we obtain the analytical results that provide the heuristics in strategies to improve the tolerance against label noise. We apply the findings into our task of learning speaker embeddings using face clusters as labels. While the experimental results agree with the analytical heuristics, there is still a large gap in performance between the supervised and the weakly supervised models, which requires further investigation in the future.

EPFL2019

Localizing Polygonal Objects in Man-Made Environments

Xiaolu Sun

Object detection is a significant challenge in Computer Vision and has received a lot of attention in the field. One such challenge addressed in this thesis is the detection of polygonal objects, which are prevalent in man-made environments. Shape analysis is an important cue to detect these objects. We propose a contour-based object detection framework to deal with the related challenges, including how to efficiently detect polygonal shapes and how to exploit them for object detection. First, we propose an efficient component tree segmentation framework for stable region extraction and a multi-resolution line segment detection algorithm, which form the bases of our detection framework. Our component tree segmentation algorithm explores the optimal threshold for each branch of the component tree, and achieves a significant improvement over image thresholding segmentation, and comparable performance to more sophisticated methods but only at a fraction of computation time. Our line segment detector overcomes several inherent limitations of the Hough transform, and achieves a comparable performance to the state-of-the-art line segment detectors. However, our approach can better capture dominant structures and is more stable against low-quality imaging conditions. Second, we propose a global shape analysis measurement for simple polygon detection and use it to develop an approach for real-time landing site detection in unconstrained man-made environments. Since the task of detecting landing sites must be performed in a few seconds or less, existing methods are often limited to simple local intensity and edge variation cues. By contrast, we show how to efficiently take into account the potential sitesâ global shape, which is a critical cue in man-made scenes. Our method relies on component tree segmentation algorithm and a new shape regularity measure to look for polygonal regions in video sequences. In this way we enforce both temporal consistency and geometric regularity, resulting in reliable and consistent detections. Third, we propose a generic contour grouping based object detection approach by exploring promising cycles in a line fragment graph. Previous contour-based methods are limited to use additive scoring functions. In this thesis, we propose an approximate search approach that eliminates this restriction. Given a weighted line fragment graph, we prune its cycle space by removing cycles containing weak nodes or weak edges, until the upper bound of the cycle space is less than the threshold defined by the cyclomatic number. Object contours are then detected as maximally scoring elementary circuits in the pruned cycle space. Furthermore, we propose another more efficient algorithm, which reconstructs the graph by grouping the strongest edges iteratively until the number of the cycles reaches the upper bound. Our approximate search approaches can be used with any cycle scoring function. Moreover, unlike other contour grouping based approaches, our approach does not rely on a greedy strategy for finding multiple candidates and is capable of finding multiple candidates sharing common line fragments. We demonstrate that our approach significantly outperforms the state-of-the-art.

EPFL2015