Large-scale instance-level image retrieval aims at retrieving specific instances of objects or scenes. Simultaneously retrieving multiple objects in a test image adds to the difficulty of the problem, especially if the objects are visually similar. This paper presents an efficient approach for per-exemplar multi-label image classification, which targets the recognition and localization of products in retail store images. We achieve runtime efficiency through the use of discriminative random forests, deformable dense pixel matching and genetic algorithm optimization. Cross-dataset recognition is performed, where our training images are taken in ideal conditions with only one single training image per product label, while the evaluation set is taken using a mobile phone in real-life scenarios in completely different conditions. In addition, we provide a large novel dataset and labeling tools for products image search, to motivate further research efforts on multi-label retail products image classification. The proposed approach achieves promising results in terms of both accuracy and runtime efficiency on 680 annotated images of our dataset, and 885 test images of GroZi-120 dataset. We make our dataset of 8350 different product images and the 680 test images from retail stores with complete annotations available to the wider community. Recently, image recognition in the retail products domain has become an interesting research topic due to the remarkable advancements in the capabilities D.
This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.
BackgroundBlood is a valuable resource and blood wastage in a low socio economic country could impose a very serious impact on healthcare. This study therefore analyzes the usage and wastage of blood and blood products at the Georgetown Public Hospital Cooperation (GPHC), Guyana.MethodsA retrospective study was conducted on the data retrieved from laboratory blood banking information system on usage and wastage of blood products during the years 2012–2014 at the public hospital. The data were analyzed in MS Excel and SPSS 20.0.ResultsA total of 16,426 units of blood were issued from National Blood Transfusion Services. During the study period the most frequently requested blood component was packed cells followed by fresh frozen plasma (FFP), platelet, cryoprecipitate (CRYO) and whole blood respectively. Data indicated that 4167 units (25 %) of blood were wasted due to various reasons at GPHC.ConclusionsThere is a need for intervention through raising awareness among medical staff in reducing blood wastage.
Assistive solutions for a better shopping experience can improve the quality of life of people, in particular also of visually impaired shoppers. We present a system that visually recognizes the fine-grained product classes of items on a shopping list, in shelves images taken with a smartphone in a grocery store. Our system consists of three components: (a) We automatically recognize useful text on product packaging, e.g., product name and brand, and build a mapping of words to product classes based on the largescale GroceryProducts dataset. When the user populates the shopping list, we automatically infer the product class of each entered word. (b) We perform fine-grained product class recognition when the user is facing a shelf. We discover discriminative patches on product packaging to differentiate between visually similar product classes and to increase the robustness against continuous changes in product design. (c) We continuously improve the recognition accuracy through active learning. Our experiments show the robustness of the proposed method against cross-domain challenges, and the scalability to an increasing number of products with minimal re-training.
Supporting human users when interacting with smart devices is important to drive the successful adoption of the Internet of Things in people's homes and at their workplaces. In this poster contribution, we present a system that helps users control Web-enabled smart things in their environment. Our approach involves a handheld interaction device that recognizes smart things in its view using state-of-the-art visual object recognition techniques. It then augments the camera feed with appropriate interaction primitives such as knobs or buttons for control, and can also display measured values, for instance, when recognizing a sensor. The interaction primitives are generated from user interface descriptions that are embedded in the Web representations of the smart things. Our prototype implementation achieves frame rates that allow for interactive use of the system by human users, and indeed proved to facilitate the interaction with smart things in a demonstration testbed in our research group.
Abstract-Manually creating an object category dataset requires a lot of hard work and wastes a large amount of time.Having an automatic means for collecting images that represent different objects is crucial for the scalable and practical expansion of these datasets. In this work, a methodology to automatically re-rank the images returned from a web search engine is proposed to improve the precision of the retrieved results. The proposed system works in an incremental way to improve the learnt object model and achieve better precision in each iteration. Images along with their meta data are ranked, then re-filtered based on their textual and visual features to produce a robust set of seed images. These images are used in learning weighted distances between the images which are used to incrementally expand the collected dataset. Using our method, we automatically gather very large object category datasets. We also improve the image ranking performance of the retrieved results over web search engines and other batch methods.
Abstract. In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for finegrained scene recognition. We first propose a semantic scene descriptor that jointly captures the subtle differences between fine-grained scenes, while being robust to varying object configurations across domains. We model the occurrence patterns of objects in scenes, capturing the informativeness and discriminability of each object for each scene. We then transform such occurrences into scene probabilities for each scene image. Second, we argue that scene images belong to hidden semantic topics that can be discovered by clustering our semantic descriptors. To evaluate the proposed method, we propose a new fine-grained scene dataset in crossdomain settings. Extensive experiments on the proposed dataset and three benchmark scene datasets show the effectiveness of the proposed approach for fine-grained scene transfer, where we outperform state-ofthe-art scene recognition and domain generalization methods.
IT is possible to obtain a radiographic view of the naso-lacrimal canal "end-on" by directing a beam of x-rays down the axis of the canal to a film held horizontally in the mouth: the centre of the film is placed near the site of the first molar tooth (Brunetti, 1930; Kopylow, 1930; Toth, 1933), or the second pre-molar. Examples of such radiographs are shown in Figs 1, 2, and 3. The present investigation has been undertaken to compare the sizes of the bony canals thus observed in a series of normal subjects with those in a series of patients with epiphora. Material Surgeons of Moorfields, Westminster and Central Eye Hospital were requested to send patients complaining of epiphora to the Radiological Department where they were x-rayed (see below). The results of syringing the naso-lacrimal passages had usually been recorded on the case-sheets; in the few cases where this information was not available for the symptomfree side in unilateral cases, a test syringing was carried out. Patients who had abnormalities of the puncta or canaliculi, or a history of facial injury involving, or operations on, the tear-passages, were excluded. It is interesting to note that four out of twenty epiphoric eyes (see Table I) had passages which were patent on syringing: the cause of epiphora in these cases was not clear. No case was recorded as having obstruction of the common canaliculus along with obstruction of the naso-lacrimal duct. The control sample was selected from patients referred for x-ray of skull, sinuses, teeth, chest, etc., for various reasons such as headaches and iridocyclitis. The same sex ratio was chosen in the control as in the affected group and each control was selected so that his or her age was within 3 years of at least one of the affected, with three exceptions: epiphorics F 78 and M 52 were not paired, and F 65 was controlled by F 60. There is no significant difference between the mean age of controls and affected (t=0-33; n=27; P very much >0-10). The affected group is thus not a random sample of epiphorics in Great Britain, and the control group is even less a random sample of individuals of the same age, sex, race, stature, etc., as the affected, but *
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.