Francesco Verdoja

Superpixel-driven graph transform for image compression

Block-based compression tends to be inefficient when blocks contain arbitrary shaped discontinuities. Recently, graph-based approaches have been proposed to address this issue, but the cost of transmitting graph topology often overcome the gain of such techniques. In this work we propose a new Superpixel-driven Graph Transform (SDGT) that uses clusters of superpixels, which have the ability to adhere nicely to edges in the image, as coding blocks and computes inside these homogeneously colored regions a graph transform which is shape-adaptive. Doing so, only the borders of the regions and the transform coefficients need to be transmitted, in place of all the structure of the graph. The proposed method is finally compared to DCT and the experimental results show how it is able to outperform DCT both visually and in term of PSNR.

Directional graph weight prediction for image compression

Graph-based models have recently attracted attention for their potential to enhance transform coding image compression thanks to their capability to efficiently represent discontinuities. Graph transform gets closer to the optimal KLT by using weights that represent inter-pixel correlations but the extra cost to provide such weights can overwhelm the gain, especially in the case of natural images rich of details. In this paper we provide a novel idea to make graph transform adaptive to the actual image content, avoiding the need to encode the graph weights as side information. We show that an approach similar to spatial prediction can be used to effectively predict graph weights in place of pixels; in particular, we propose the design of directional graph weight prediction modes and show the resulting coding gain. The proposed approach can be used jointly with other graph based intra prediction methods to further enhance compression. Our comparative experimental analysis, carried out with a fully fledged still image coding prototype, shows that we are able to achieve significant coding gains.

Automatic method for tumor segmentation from 3-points dynamic PET acquisitions

In this paper a novel technique to segment tumor voxels in dynamic positron emission tomography (PET) scans is proposed. An innovative anomaly detection tool tailored for 3-points dynamic PET scans is designed. The algorithm allows the identification of tumoral cells in dynamic FDG-PET scans thanks to their peculiar anaerobic metabolism experienced over time. The proposed tool is preliminarily tested on a small dataset showing promising performance as compared to the state of the art in terms of both accuracy and classification errors.

Fast Superpixel-Based Hierarchical Approach to Image Segmentation

Image segmentation is one of the core task in image processing. Traditionally such operation is performed starting from single pixels requiring a significant amount of computations. It has been shown that superpixels can be used to improve segmentation performance. In this work we propose a novel superpixel-based hierarchical approach for image segmentation that works by iteratively merging nodes of a weighted undirected graph initialized with the superpixels regions. Proper metrics to drive the regions merging are proposed and experimentally validated using the standard Berkeley Dataset. Our analysis shows that the proposed algorithm runs faster than state of the art techniques while providing accurate segmentation results both in terms of visual and objective metrics.

Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding

Segmentation of 3D colored point clouds is a research field with renewed interest thanks to recent availability of inexpensive consumer RGB-D cameras and its importance as an unavoidable low-level step in many robotic applications. However, 3D datas nature makes the task challenging and, thus, many different techniques are being proposed, all of which require expensive computational costs. This paper presents a novel fast method for 3D colored point cloud segmentation. It starts with supervoxel partitioning of the cloud, i.e., an oversegmentation of the points in the cloud. Then it leverages on a novel metric exploiting both geometry and color to iteratively merge the supervoxels to obtain a 3D segmentation where the hierarchical structure of partitions is maintained. The algorithm also presents computational complexity linear to the size of the input. Experimental results over two publicly available datasets demonstrate that our proposed method outperforms state-of-the-art techniques.

Efficient representation of segmentation contours using chain codes

Segmentation is one of the most important low-level tasks in image processing as it enables many higher level computer vision tasks like object recognition and tracking. Segmentation can also be exploited for image compression using recent graph-based algorithms, provided that the corresponding contours can be represented efficiently. Transmission of borders is also key to distributed computer vision. In this paper we propose a new chain code tailored to compress segmentation contours. Based on the widely known 3OT, our algorithm is able to encode regions avoiding borders it has already coded once and without the need of any starting point information for each region. We tested our method against three other state of the art chain codes over the BSDS500 dataset, and we demonstrated that the proposed chain code achieves the highest compression ratio, resulting on average in over 27% bit-per-pixel saving.