This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

/pdf/distinctive-image-features-from-scale-invariant-keypoints-3waurjqzke.pdf

Distinctive Image Features from Scale-Invariant Keypoints

Fiji is a distribution of the popular open-source software ImageJ focused on biological-image analysis. Fiji uses modern software engineering practices to combine powerful software libraries with a broad range of scripting languages to enable rapid prototyping of image-processing algorithms. Fiji facilitates the transformation of new algorithms into ImageJ plugins that can be shared with end users through an integrated update system. We propose Fiji as a platform for productive collaboration between computer science and biology research communities.

/pdf/fiji-an-open-source-platform-for-biological-image-analysis-1v529iu3cx.pdf

Fiji: an open-source platform for biological-image analysis

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

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.

The problem of different training and test set class priors is addressed in the context of CNN classifiers. We compare two different approaches to estimating the new priors: an existing Maximum Likelihood Estimation approach (optimized by an EM algorithm or by projected gradient descend) and a proposed Maximum a Posteriori approach, which increases the stability of the estimate by introducing a Dirichlet hyper-prior on the class prior probabilities. Experimental results show a significant improvement on the fine-grained classification tasks using known evaluation-time priors, increasing the top-1 accuracy by 4.0% on the FGVC iNaturalist 2018 validation set and by 3.9% on the FGVCx Fungi 2018 validation set. Estimation of the unknown test set priors noticeably increases the accuracy on the PlantCLEF dataset, allowing a single CNN model to achieve state-of-the-art results and outperform the competition-winning ensemble of 12 CNNs. The proposed Maximum a Posteriori estimation increases the prediction accuracy by 2.8% on PlantCLEF 2017 and by 1.8% on FGVCx Fungi, where the existing MLE method would lead to a decrease accuracy.

Improving CNN classifiers by estimating test-time priors

A method that employs grammars to direct the inference process of a vision system that does interpretation of dynamic scenes is described. The system uses a set of qualitative image descriptors to drive the interpretation. The result is a 'natural language' description of scene activities. In addition the inference engine generates a set of predictions that can be used to control the interpretation strategy so as to make the processing of new images more efficient. The system has been implemented in an expert system shell to demonstrate the viability of the approach. Results on real images are reported.

/pdf/using-grammars-for-scene-interpretation-382kyd7svy.pdf

Using grammars for scene interpretation

The multimodal neighbourhood signature (MNS) algorithm represents local object appearance by stable colour-based invariants efficiently computed from image neighbourhoods with multimodal colour density function. Local feature extraction facilitates region-based interactive query specification and computation of illumination invariant features. The method allows for fast signature matching and supports retrieval of objects covering only a fraction of the database image. MNS signatures are generally compact and storage requirements are typically a few hundred bytes per image. In this paper, the proposed algorithm is tested on a challenging region-based image retrieval task, searching for objects in a sports video sequence. Image regions depicting objects of typical interest in a sports image database are delineated by the users and used as queries. Acceptable retrieval results are presented for a number of experiments. Relevant images were retrieved regardless of background clutter dominating the scene, partial occlusion and/or non-rigid object deformation. Finally, the suitability of the approach is investigated in the context of webbased applications where efficient signature creation, good matching speed and minimal storage requirements are required.

/pdf/colour-based-image-retrieval-from-video-sequences-35efjw3txc.pdf

Colour-based Image Retrieval from Video Sequences

The article presents an AI-based fungi species recognition system for a citizen-science community. The system’s real-time identification too — FungiVision — with a mobile application front-end, led to increased public interest in fungi, quadrupling the number of citizens collecting data. FungiVision, deployed with a human-in-the-loop, reaches nearly 93% accuracy. Using the collected data, we developed a novel fine-grained classification dataset — Danish Fungi 2020 (DF20) — with several unique characteristics: species-level labels, a small number of errors, and rich observation metadata. The dataset enables the testing of the ability to improve classification using metadata, e.g., time, location, habitat and substrate, facilitates classifier calibration testing and finally allows the study of the impact of the device settings on the classification performance. The continual flow of labelled data supports improvements of the online recognition system. Finally, we present a novel method for the fungi recognition service, based on a Vision Transformer architecture. Trained on DF20 and exploiting available metadata, it achieves a recognition error that is 46.75% lower than the current system. By providing a stream of labeled data in one direction, and an accuracy increase in the other, the collaboration creates a virtuous cycle helping both communities.

/pdf/automatic-fungi-recognition-deep-learning-meets-mycology-1mfku8jo.pdf

Automatic Fungi Recognition: Deep Learning Meets Mycology

This paper describes a study for a real time embedded face detection system Recently, the boosting based face detection algorithms proposed by [(Viola, P and Jone, M, 2001); (Lienhart, R, et al, 2003)] have gained a lot of attention and are considered as the fastest accurate face detection algorithms today However, the embedded implementation of such algorithms into hardware is still a challenge, since these algorithms are heavily based on memory access A sequential implementation model is built showing its lack of regularity in time consuming and speed of detection We propose a parallel implementation that exploits the parallelism and the pipelining in these algorithms This implementation proves capable of increasing the speed of the detector as well as bringing regularity in time consuming

Jiri Matas

Papers

Improving CNN classifiers by estimating test-time priors

Using grammars for scene interpretation

Colour-based Image Retrieval from Video Sequences

Automatic Fungi Recognition: Deep Learning Meets Mycology

Embedded System Study for Real Time Boosting Based Face Detection