A Hybrid Approach for Product Classification based on Image and Text Matching.
Sebastian BastChristoph BroschRolf KriegerPublished in: DATA (2022)
Keyphrases
- image classification
- image matching
- image data
- template matching
- matching process
- input image
- image set
- image features
- image analysis
- feature matching
- single image
- feature points
- extracting features
- matching algorithm
- pattern recognition
- image representation
- supervised machine learning
- image retrieval
- image segmentation
- normalized correlation
- image content
- fourier descriptors
- multiscale
- classification accuracy
- string matching
- preprocessing stage
- text classification
- matching scheme
- extracted features
- high resolution
- image collections
- machine learning
- spatial pyramid matching
- feature representation
- scanned documents
- scene matching
- information retrieval
- affine invariant
- image regions
- keypoints
- object recognition
- decision trees
- region of interest
- pattern matching
- geometric transformations
- text mining
- support vector machine
- color images
- training set
- false matches
- image sequences
- feature selection
- thematic mapper