Sökning: "Content Based Image Retrieval"

Visar resultat 1 - 5 av 18 uppsatser innehållade orden Content Based Image Retrieval.

1. 1. Evaluating Transfer Learning Models on Synthetic Data for Beverage Label Image Retrieval : A Comparative Study

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Anton Brask; [2022]
   Nyckelord :;

   Sammanfattning : Information retrieval is a research area that has seen improvements with the development of deep learning and artificial neural networks. The vast amount of image data available today has made it possible to train computer vision models for efficient image search. LÄS MER

3. 2. News article segmentation using multimodal input : Using Mask R-CNN and sentence transformers

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Gustav Henning; [2022]
   Nyckelord :Historical newspapers; Image segmentation; Multimodal learning; Deep learning; Digital humanities; Mask R-CNN; Historiska tidningar; Bildsegmentering; Multimodal inlärning; Djupinlärning; Digital humaniora; Mask R-CNN;

   Sammanfattning : In this century and the last, serious efforts have been made to digitize the content housed by libraries across the world. In order to open up these volumes to content-based information retrieval, independent elements such as headlines, body text, bylines, images and captions ideally need to be connected semantically as article-level units. LÄS MER

4. 3. Object Based Image Retrieval Using Feature Maps of a YOLOv5 Network

   Master-uppsats, KTH/Matematisk statistik

   Författare :Hugo Essinger; Alexander Kivelä; [2022]
   Nyckelord :Content based image retrieval; CBIR; Object based image retrieval; OBIR; image retrieval; YOLO; YOLOv5; object detection; PyTorch; deep learning; convolutional neural network; CNN; Content based image retrieval; CBIR; Object based image retrieval; OBIR; image retrieval; YOLO; YOLOv5; object detection; PyTorch; deep learning; convolutional neural network; CNN;

   Sammanfattning : As Machine Learning (ML) methods have gained traction in recent years, someproblems regarding the construction of such methods have arisen. One such problem isthe collection and labeling of data sets. Specifically when it comes to many applicationsof Computer Vision (CV), one needs a set of images, labeled as either being of someclass or not. LÄS MER

5. 4. Self-Supervised Representation Learning for Content Based Image Retrieval

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Hariprasath Govindarajan; [2020]
   Nyckelord :Content Based Image Retrieval; CBIR; Representation Learning; Self Supervised Learning; Unsupervised Learning; Attention Mechanism; Noise Contrastive Estimation; Autonomous Driving;

   Sammanfattning : Automotive technologies and fully autonomous driving have seen a tremendous growth in recent times and have benefitted from extensive deep learning research. State-of-the-art deep learning methods are largely supervised and require labelled data for training. LÄS MER

7. 5. Feature Extraction for ContentBased Image Retrieval Using a PreTrained Deep Convolutional Neural Network

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Leonard Halling; [2020]
   Nyckelord :;

   Sammanfattning : This thesis examines the performance of features, extracted from a pre-trained deep convolutional neural network, for content-based image retrieval in images of news articles. The industry constantly awaits improved methods for image retrieval, including the company hosting this research project, who are looking to improve their existing image description-based method for image retrieval. LÄS MER