Saillance | EPFL Graph Search

La saillance (de l'anglais salience, construit sur salient, du français saillant, lui-même du latin saliens, « qui saute ») d'une chose quelconque est le fait qu'elle attire l'attention ; plus précisément, la mesure dans laquelle elle retient l'attention par rapport aux autres choses présentes dans son environnement (y compris des choses similaires). Par exemple, un mot peut être mieux perçu que d'autres dans un message (saillance linguistique). Dans une représentation visuelle comme une affiche ou une cartographie, certains éléments peuvent ressortir plus que d'autres (saillance visuelle). Certaines annonces sonores peuvent être mieux perçues que d'autres (saillance sonore). L'effet Von Restorff, postulé dès 1933, prévoit qu'un item avec une saillance élevée sera plus susceptible d'être retenu. Saillance linguistique Les mots peuvent avoir une saillance intrinsèque, par exemple selon leur prononciation, mais la saillance dépend aussi de leur place et de leur fonction dans

We get the algorithms of our ground truths: Designing referential databases in digital image processing

Florian Lucas Jaton

This article documents the practical efforts of a group of scientists designing an imageprocessing algorithm for saliency detection. By following the actors of this computer science project, the article shows that the problems often considered to be the starting points of computational models are in fact provisional results of time-consuming, collective and highly material processes that engage habits, desires, skills and values. In the project being studied, problematization processes lead to the constitution of referential databases called ‘ground truths’ that enable both the effective shaping of algorithms and the evaluation of their performances. Working as important common touchstones for research communities in image processing, the ground truths are inherited from prior problematization processes and may be imparted to subsequent ones. The ethnographic results of this study suggest two complementary analytical perspectives on algorithms: (1) an ‘axiomatic’ perspective that understands algorithms as sets of instructions designed to solve given problems computationally in the best possible way, and (2) a ‘problem-oriented’ perspective that understands algorithms as sets of instructions designed to computationally retrieve outputs designed and designated during specific problematization processes. If the axiomatic perspective on algorithms puts the emphasis on the numerical transformations of inputs into outputs, the problem-oriented perspective puts the emphasis on the definition of both inputs and outputs

SAGE Publications2017

Are All Pixels Equally Important? Towards Multi-Level Salient Object Detection

Gökhan Yildirim

When we look at our environment, we primarily pay attention to visually distinctive objects. We refer to these objects as visually important or salient. Our visual system dedicates most of its processing resources to analyzing these salient objects. An analogous resource allocation can be performed in computer vision, where a salient object detector identifies objects of interest as a pre-processing step. In the literature, salient object detection is considered as a foreground-background segmentation problem. This approach assumes that there is no variation in object importance. Only the most salient object(s) are detected as foreground. In this thesis, we challenge this conventional methodology of salient-object detection and introduce multi-level object saliency. In other words, all pixels are not equally important. The well-known salient-object ground-truth datasets contain images with single objects and thus are not suited to evaluate the varying importance of objects. In contrast, many natural images have multiple objects. The saliency levels of these objects depend on two key factors. First, the duration of eye fixation is longer for visually and semantically informative image regions. Therefore, a difference in fixation duration should reflect a variation in object importance. Second, visual perception is subjective; hence the saliency of an object should be measured by averaging the perception of a group of people. In other words, objective saliency can be considered as the collective human attention. In order to better represent natural images and to measure the saliency levels of objects, we thus collect new images containing multiple objects and create a Comprehensive Object Saliency (COS) dataset. We provide ground truth multi-level salient object maps via eye-tracking and crowd-sourcing experiments. We then propose three salient-object detectors. Our first technique is based on multi-scale linear filtering and can detect salient objects of various sizes. The second method uses a bilateral-filtering approach and is capable of producing uniform object saliency values. Our third method employs image segmentation and machine learning and is robust against image noise and texture. This segmentation-based method performs the best on the existing datasets compared to our other methods and the state-of-the-art methods. The state-of-the-art salient-object detectors are not designed to assess the relative importance of objects and to provide multi-level saliency values. We thus introduce an Object-Awareness Model (OAM) that estimates the saliency levels of objects by using their position and size information. We then modify and extend our segmentation-based salient-object detector with the OAM and propose a Comprehensive Salient Object Detection (CSD) method that is capable of performing multi-level salient-object detection. We show that the CSD method significantly outperforms the state-of-the-art methods on the COS dataset. We use our salient-object detectors as a pre-processing step in three applications. First, we show that multi-level salient-object detection provides more relevant semantic image tags compared to conventional salient-object detection. Second, we employ our salient-object detector to detect salient objects in videos in real time. Third, we use multi-level object-saliency values in context-aware image compression and obtain perceptually better compression compared to standard JPEG with the same file size.

EPFL2015

Are All Pixels Equally Important? Towards Multi-Level Salient Object Detection

Gökhan Yildirim

EPFL2015