Francisco J. Estrada

Frequency-tuned salient region detection

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.

Salient region detection and segmentation

Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image. We demonstrate the use of the algorithm in the segmentation of semantically meaningful whole objects from digital images.

Benchmarking Image Segmentation Algorithms

We present a thorough quantitative evaluation of four image segmentation algorithms on images from the Berkeley Segmentation Database. The algorithms are evaluated using an efficient algorithm for computing precision and recall with regard to human ground-truth boundaries. We test each segmentation method over a representative set of input parameters, and present tuning curves that fully characterize algorithm performance over the complete image database. We complement the evaluation on the BSD with segmentation results on synthetic images. The results reported here provide a useful benchmark for current and future research efforts in image segmentation.

Quantitative evaluation of a novel image segmentation algorithm

We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley segmentation database as ground truth and propose suitable measures to evaluate segmentation quality. With these measures we generate precision/recall curves for SE-MinCut and three of the leading segmentation algorithms: mean-shift, normalized Cuts, and the local variation algorithm. These curves characterize the performance of each algorithm over a range of input parameters. We compare the precision/recall curves for the four algorithms and show segmented images that support the conclusions obtained from the quantitative evaluation.

Stochastic Image Denoising.

We present a novel algorithm for image denoising. Our algorithm is based on random walks over arbitrary neighbourhoods surrounding a given pixel. The size and shape of each neighbourhood are determined by the configuration and similarity of nearby pixels. Assuming that pixels within the neighbourhood of x0 are likely to have been generated by the same random process, we want the weights used to mix these pixels during denoising to depend on the similarity between them and x0. At the same time, we require the random walk to follow a smooth path from x0 to any other pixel in the neighbourhood, so the transition probabilities should also depend on the similarity between pairs of neighbouring pixels along any given path. With this in mind, we define a random walk originating at pixel x0 as an ordered sequence of pixels T0,k = {x0,x1, . . . ,xk} visited along the path from x0 to xk. Within this sequence, the probability of a transition between two consecutive pixels x j and x j+1 is defined to be

Perceptual grouping for contour extraction

This paper describes an algorithm that efficiently groups line segments into perceptually salient contours in complex images. A measure of affinity between pairs of lines is used to guide group formation and limit the branching factor of the contour search procedure. The extracted contours are ranked, and presented as a contour hierarchy. Our algorithm is able to extract salient contours in the presence of texture, clutter, and repetitive or ambiguous image structure. We show experimental results on a complex line-set.

Multi-Scale Contour Extraction Based on Natural Image Statistics

Perceptual grouping of the complete boundaries of objects in natural images remains an unsolved problem in computer vision. The computational complexity of the problem and difficulties capturing global constraints limit the performance of current algorithms. In this paper we develop a coarse-to-fine Bayesian algorithm which addresses these constraints. Candidate contours are extracted at a coarse scale and then used to generate spatial priors on the location of possible contours at finer scales. In this way, a rough estimate of the shape of an object is progressively refined. The coarse estimate provides robustness to texture and clutter while the refinement process allows for the extraction of detailed object contours. The grouping algorithm is probabilistic and uses multiple grouping cues derived from natural scene statistics. We present a quantitative evaluation of grouping performance on the Berkeley Segmentation Database, and show that the multi-scale approach outperforms several single-scale contour extraction algorithms.

Spectral Embedding and Min-Cut for Image Segmentation

Recently it has been shown that min-cut algorithms can provide perceptually salient image segments when they are given appropriate proposals for source and sink regions. Here we explore the use of random walks and associated spectral embedding techniques for the automatic generation of suitable proposal regions. To do this, we first derive a mathematical connection between spectral embedding and anisotropic image smoothing kernels. We then use properties of the spectral embedding and the associated smoothing kernels to select multiple pairs of source and sink regions for min-cut. This typically provides an over-segmentation, and therefore region merging is used to form the final image segmentation. We demonstrate this process on several sample images.

Appearance-based keypoint clustering

We present an algorithm for clustering sets of detected interest points into groups that correspond to visually distinct structure. Through the use of a suitable colour and texture representation, our clustering method is able to identify keypoints that belong to separate objects or background regions. These clusters are then used to constrain the matching of keypoints over pairs of images, resulting in greatly improved matching under difficult conditions. We present a thorough evaluation of each component of the algorithm, and show its usefulness on difficult matching problems.

Robust Boundary DetectionWith Adaptive Grouping

This paper presents a perceptual grouping algorithm that performs boundary extraction on natural images. Our grouping method maintains and updates a model of the appearance of the image regions on either side of a growing contour. This model is used to change grouping behaviour at run-time, so that, in addition to following the traditional Gestalt grouping principles of proximity and good continuation, the grouping procedure favours the path that best separates two visually distinct parts of the image. The resulting algorithm is computationally efficient and robust to clutter and texture. We present experimental results on natural images from the Berkeley Segmentation Database and compare our results to those obtained with three alternate grouping methods.