English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Current work in object categorization discriminates among objects that typically possess gross differences which are readily apparent. However, many applications require making much finer distinctions. We address an in- sect categorization problem that is so challenging that eve n trained human experts cannot readily categorize the insect s based on their images. The state of the art that uses visual dictionaries, when applied to this problem, yields mediocr e results (16.1% error). Three possible explanations for thi s are (a) the dictionaries are unsupervised, (b) the dictio- naries lose the detailed information contained in each key- point, and (c) these methods rely on hand-engineered de- cisions about dictionary size. This paper presents a novel, dictionary-free methodology. A random forest of trees is first trained to predict the class of an image based on indi- vidual keypoint descriptors. A unique aspect of these trees is that they do not makedecisions but instead merely record evidence—i.e., the number of descriptors from training ex- amples of each category that reached each leaf of the tree. We provide a mathematical model showing that voting evi- dence is better than voting decisions. To categorize a new image, descriptors for all detected keypoints are "dropped " through the trees, and the evidence at each leaf is summed to obtain an overall evidence vector. This is then sent to a second-level classifier to make the categorization decisio n. We achieve excellent performance (6.4% error) on the 9- class STONEFLY9 data set. Also, our method achieves an average AUC of 0.921 on the PASCAL06 VOC, which places it fifth out of 21 methods reported in the literature and demonstrates that the method also works well for generic object categorization.

Dictionary-free categorization of very similar objects via stacked evidence trees