Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “image classification”

Image Classification

Akshay Kulkarni, Adarsha Shivananda, Nitin Ranjan Sharma · Apress eBooks · 2022

The last chapter discussed several important concepts in computer vision. A few of the best practices in the field of computer vision were discussed as well, so it is time to practice those. This chapter sets the tone for multiple tasks in the field of computer vision. We start with a basic explanation of how to start using the Torch components to build a model, define a loss function, and train.

Cited by 1

Image Classification

Michael Paluszek, Stephanie Thomas, Eric Ham · Apress eBooks · 2022

AlexNet is a pretrained convolutional neural network (CNN) that has been trained on approximately 1.2 million images from the ImageNet Dataset ( http://image-net.org/index ). The model has 25 layers and can classify images into 1000 object categories. It can be used for all sorts of object classification. However, if an object was not in the training set, it won’t be able to identify the object. If a banana was in the training set, you could expect the CNN to correctly identify a new picture of a banana. But if you gave it a picture of a plantain, and plantain was NOT in the CNN, then it might not find a match or, more likely, it might incorrectly classify it like a banana.

Cited by 0

Image classification

Dustin Wright (7350995), Isabelle Augenstein (14013962) · Figshare · 2025

The training dataset for image classification comes from the 10,000 images in the CIFAR10 test set re-annotated by crowd workers on Amazon Mecahnical Turk (AMT) [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0323064#pone.0323064.ref002" target="_blank">2</a>]. The final dataset contains 511,400 annotations, with 51 annotations on average per image, and an IAA of 0.91 Krippendorff’s . For the test data, we use the CINIC10 dataset [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0323064#pone.0323064.ref028" target="_blank">28</a>], which contains 210,000 images from Imagenet rescaled down to 32x32 to match the CIFAR10 image size. Here, distribution shift comes from the data distribution (source: CIFAR10 images, target: scaled down Imagenet images). (PDF)

Cited by 0Open access

Image Classification

Éric Trupin, Aia Sa · 2014

Abstract. This paper presents a semi-supervised document image classification system that aims to be integrated into a commercial document reading software. This system is asserted like an annotation help. From a set of unknown document images given by a human operator, the system computes regrouping hypothesis of same physical layout images and proposes them to the operator. Then he can correct them, validate them, keeping in mind that his objective is to have homogeneous groups of images. These groups will be used for the training of the supervised document image classifier. Our system contains N feature spaces and a metric function for each of them. These allow to compute the similarity between two points of the same space. After projecting each image in these N feature spaces, the system builds N hierarchical agglomerative classification trees (hac) corresponding to each feature space. The proposals for regroupings formulated by the various hac are confronted and merged. Results, evaluated by the number of corrections done by the operator are presented on different image sets. 1

Cited by 0

classification image

永井 聖剛, 齋木 潤, 渡邊 克巳 · The Proceedings of the Annual Convention of the Japanese Psychological Association · 2006

Cited by 0Open access

Image classification

T. Kevin O&amp;apos;donnell, Keith W. Goyne, Randall J. Miles et al. · 2011

Determination of representative elementary areas for soil redoximorphic features identified by digital image processing

Cited by 0

for Image Classification

Paolo Piro, Richard Nock, Frank Nielsen et al. · 2012

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Multi-Class Leveraged k-NN

Cited by 0

Color Image Classification

Marcel J. Castro, Advisors Vidya Manian, Ramón Vásquez · 1999

This paper describes the process of classifying color images based on color texture information. The images are originally in Red-Green-Blue (RGB) and they are changed to xyY to facilitate the image processing. Chromacity information (xy) is combined with luminance (Y) in the image. Luminance and chrominance image processing implementation is included in this paper. The process analyzes them separately to finally use them both together to classify the image. Luminance information is processed in three stages: filtering, smoothing, and boundary detection. Chrominance information on the other hand, is processed in one stage: histogram multi-thresholding. Classification based on luminance is done by Gabor filtering and then calculating the approximately features. Results are presented for 6 color images. 1.

Cited by 0

Automatic image classification

Ševčík, Zdeněk · Brno University of Technology Digital Library (Brno University of Technology) · 2020

Cílem této práce je prozkoumat shlukovací algoritmy strojového učení bez učitele, které lze použít pro klasifikaci databáze obrazů podle podobnosti. Pro vybrané shlukovací algoritmy je sepsán teoretický základ. Pro zlepšení klasifikace použité databáze se diplomová práce zabývá různými metodami předzpracování obrazů. Těmito metodami jsou z obrazu extrahovány příznaky. Dále práce řeší implementaci metod předzpracování a praktickou aplikaci shlukovacích algoritmů. V praktické části je naprogramována aplikace v programovacím jazyce Python, která klasifikuje databázi obrazů do tříd podle podobnosti. Diplomová práce testuje všechny použité metody a ke konci práce je zpracována rešerše výsledků.

Cited by 0