We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

http://library.utia.cas.cz/prace/20030125.pdf

Image registration methods: a survey

This paper investigates two fundamental problems in computer vision: contour detection and image segmentation. We present state-of-the-art algorithms for both of these tasks. Our contour detector combines multiple local cues into a globalization framework based on spectral clustering. Our segmentation algorithm consists of generic machinery for transforming the output of any contour detector into a hierarchical region tree. In this manner, we reduce the problem of image segmentation to that of contour detection. Extensive experimental evaluation demonstrates that both our contour detection and segmentation methods significantly outperform competing algorithms. The automatically generated hierarchical segmentations can be interactively refined by user-specified annotations. Computation at multiple image resolutions provides a means of coupling our system to recognition applications.

/pdf/contour-detection-and-hierarchical-image-segmentation-2ejknw01zo.pdf

Contour Detection and Hierarchical Image Segmentation

Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations. The well-known structural similarity index brings IQA from pixel- to structure-based stage. In this paper, a novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS' perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA databases demonstrate that FSIM can achieve much higher consistency with the subjective evaluations than state-of-the-art IQA metrics.

/pdf/fsim-a-feature-similarity-index-for-image-quality-assessment-42wiyfodry.pdf

FSIM: A Feature Similarity Index for Image Quality Assessment

This paper describes a new approach to low level image processing; in particular, edge and corner detection and structure preserving noise reduction.

Non-linear filtering is used to define which parts of the image are closely related to each individual pixel; each pixel has associated with it a local image region which is of similar brightness to that pixel. The new feature detectors are based on the minimization of this local image region, and the noise reduction method uses this region as the smoothing neighbourhood. The resulting methods are accurate, noise resistant and fast.

Details of the new feature detectors and of the new noise reduction method are described, along with test results.

SUSAN—A New Approach to Low Level Image Processing

Feature detection from local energy

Viewpoint independent recognition of free-form objects and their segmentation in the presence of clutter and occlusions is a challenging task. We present a novel 3D model-based algorithm which performs this task automatically and efficiently. A 3D model of an object is automatically constructed offline from its multiple unordered range images (views). These views are converted into multidimensional table representations (which we refer to as tensors). Correspondences are automatically established between these views by simultaneously matching the tensors of a view with those of the remaining views using a hash table-based voting scheme. This results in a graph of relative transformations used to register the views before they are integrated into a seamless 3D model. These models and their tensor representations constitute the model library. During online recognition, a tensor from the scene is simultaneously matched with those in the library by casting votes. Similarity measures are calculated for the model tensors which receive the most votes. The model with the highest similarity is transformed to the scene and, if it aligns accurately with an object in the scene, that object is declared as recognized and is segmented. This process is repeated until the scene is completely segmented. Experiments were performed on real and synthetic data comprised of 55 models and 610 scenes and an overall recognition rate of 95 percent was achieved. Comparison with the spin images revealed that our algorithm is superior in terms of recognition rate and efficiency

Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes

We present a fully automatic face recognition algorithm and demonstrate its performance on the FRGC v2.0 data. Our algorithm is multimodal (2D and 3D) and performs hybrid (feature based and holistic) matching in order to achieve efficiency and robustness to facial expressions. The pose of a 3D face along with its texture is automatically corrected using a novel approach based on a single automatically detected point and the Hotelling transform. A novel 3D spherical face representation (SFR) is used in conjunction with the scale-invariant feature transform (SIFT) descriptor to form a rejection classifier, which quickly eliminates a large number of candidate faces at an early stage for efficient recognition in case of large galleries. The remaining faces are then verified using a novel region-based matching approach, which is robust to facial expressions. This approach automatically segments the eyes- forehead and the nose regions, which are relatively less sensitive to expressions and matches them separately using a modified iterative closest point (ICP) algorithm. The results of all the matching engines are fused at the metric level to achieve higher accuracy. We use the FRGC benchmark to compare our results to other algorithms that used the same database. Our multimodal hybrid algorithm performed better than others by achieving 99.74 percent and 98.31 percent verification rates at a 0.001 false acceptance rate (FAR) and identification rates of 99.02 percent and 95.37 percent for probes with a neutral and a nonneutral expression, respectively.

An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition

3D object recognition from local features is robust to occlusions and clutter However, local features must be extracted from a small set of feature rich keypoints to avoid computational complexity and ambiguous features We present an algorithm for the detection of such keypoints on 3D models and partial views of objects The keypoints are highly repeatable between partial views of an object and its complete 3D model We also propose a quality measure to rank the keypoints and select the best ones for extracting local features Keypoints are identified at locations where a unique local 3D coordinate basis can be derived from the underlying surface in order to extract invariant features We also propose an automatic scale selection technique for extracting multi-scale and scale invariant features to match objects at different unknown scales Features are projected to a PCA subspace and matched to find correspondences between a database and query object Each pair of matching features gives a transformation that aligns the query and database object These transformations are clustered and the biggest cluster is used to identify the query object Experiments on a public database revealed that the proposed quality measure relates correctly to the repeatability of keypoints and the multi-scale features have a recognition rate of over 95% for up to 80% occluded objects

/pdf/on-the-repeatability-and-quality-of-keypoints-for-local-19x01qtbbv.pdf

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

Fat in human milk is extremely variable and can represent up to 50 % of infant energy intake. To accurately determine milk composition and infant intake at 1 (n 17), 2 (n 17), 4 (n 17), 6 (n 15), 9 (n 6) and 12 (n 5) months of lactation, samples of fore- and hind-milk were collected from each breast at each feed over 24 h periods from an initial group of seventeen women. The content of fat in milk varied over 24 h, with a mean CV of 47·6 (SE 2·1) % (n 76) and 46·7 (SE 1·7) % (n 76) for left and right breasts respectively. The 24 h amounts of fat, lactose and protein in milk differed between women (Pa0·0001), but were consistent between left and right breasts. Daily milk production differed between breasts (Pa0·0001) and women (Pa 0·0001). Accordingly, amounts of fat (Pa0·0008), lactose (Pa0·0385) and protein (Pa0·0173) delivered to the infant over 24 h also differed between breasts and women (Pa0·0001). The energy content of milk and the amount of energy delivered to the infant over 24 h were the same between breasts, but differed between women (Pa 0·0001). The growth rate of a group of only six infants in the present study was not related to either the concentrations or amounts of fat, lactose, protein and energy in milk over the first 6 months of life. These results show the individuality of milk composition and suggest that only a rigorous sampling routine that takes into account all levels of variation will allow the accurate determination of infant intake of fat, lactose, protein and energy. Milk fat: Infant intake: Sampling routine: Human lactation

/pdf/variation-in-fat-lactose-and-protein-in-human-milk-over-24-h-kxrhfe5w8g.pdf

Robyn Owens

Papers

Feature detection from local energy

Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes

An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition

On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes

Variation in fat, lactose and protein in human milk over 24 h and throughout the first year of lactation.