Object classification from a photographic image is a complex process and is fast becoming an important task in the field of computer vision. Real-time object classification from images has been used in various fields such as healthcare, manufacturing, retail, etc. Object classification from photographic images is a technique that includes classifying or predicting the class of an object in an image, with a goal to accurately identify the feature in an image. Object classification includes labelling and classifying the images into predefined classes based on the feature/object observed. Object Classification from images is an important application in the domain of Computer Vision and the field involves different techniques and algorithms to acquire, analyse, and process the images. To put it common terms, Object Classification from images is a process of classifying and predicting the class of the objects in an image, with a goal to unambiguously distinguish the feature/object in the image. In general, object classification is an algorithm that takes in a set of features that represent the objects in the image and makes use of the same to predict the class for each object.
Recent results of deep convolutional networks in visual recognition challenges open the path to a whole new set of disruptive user experiences such as visual search or recommendation. The list of companies offering this type of service is growing everyday but the adoption rate and the relevancy of results may vary a lot. We believe that the availability of large and diverse datasets is a necessary condition to improve the relevancy of such recommendation systems and facilitate their adoption. For that purpose, we wish to share with the community this dataset of more than 12M images of the 7M products of our online store classified into 5K categories. This original dataset is introduced in this article and several features are described. We also present some aspects of the winning solutions of our image classification challenge that was organized on the Kaggle platform around this set of images.
Computer vision will play a crucial role in visual search, self-driving cars, medicine and many other applications. Success will hinge on collecting and labeling large labeled datasets which will be used to train and test new algorithms. One area that has seen great advances over the last five years is image classification i.e. determining automatically what objects are present in an image. Existing image classification datasets have an equal number of images for each class. However, the real world is long tailed: only a small percentage of classes are likely to be observed; most classes are infrequent or rare.
This paper proposes an inexpensive way to learn an effective dissimilarity function to be used for $k$-nearest neighbor ($k$-NN) classification. Unlike Mahalanobis metric learning methods that map both query (unlabeled) objects and labeled objects to new coordinates by a single transformation, our method learns a transformation of labeled objects to new points in the feature space whereas query objects are kept in their original coordinates. This method has several advantages over existing distance metric learning methods: (i) In experiments with large document and image datasets, it achieves $k$-NN classification accuracy better than or at least comparable to the state-of-the-art metric learning methods. (ii) The transformation can be learned efficiently by solving a standard ridge regression problem. For document and image datasets, training is often more than two orders of magnitude faster than the fastest metric learning methods tested. This speed-up is also due to the fact that the proposed method eliminates the optimization over "negative" object pairs, i.e., objects whose class labels are different. (iii) The formulation has a theoretical justification in terms of reducing hubness in data.
Sequence classification plays an important role in metagenomics studies. We assess the deep neural network approach for fungal sequence classification as it has emerged as a successful paradigm for big data classification and clustering. Two deep learning-based classifiers, a convolutional neural network (CNN) and a deep belief network (DBN) were trained using our recently released barcode datasets. Experimental results show that CNN outperformed the traditional BLAST classification and the most accurate machine learning based Ribosomal Database Project (RDP) classifier on datasets that had many of the labels present in the training datasets. When classifying an independent dataset namely the “Top 50 Most Wanted Fungi”, CNN and DBN assigned less sequences than BLAST. However, they could assign much more sequences than the RDP classifier. In terms of efficiency, it took the machine learning classifiers up to two seconds to classify a test dataset while it was 53 s for BLAST. The result of the current study will enable us to speed up the taxonomic assignments for the fungal barcode sequences generated at our institute as ~ 70% of them still need to be validated for public release. In addition, it will help to quickly provide a taxonomic profile for metagenomics samples.