First we already observed an advantage for global domain categories using scene categories: there was a speed advantage for distinguishing between natural and man-made environments whereas reaching a decision at more detailed levels (sea, mountain, indoor or outdoor environments) required a longer processing time [41].
This deep learning model achieves better results because it improves performance on some major problems, including limited data amount and categories, scenes dependent evaluation, unbalanced dataset, noise data etc.
These fall into two categories: scenes cut before any public screenings of the film, and scenes cut a few days after the world premiere on April 2 , 1968
In this study, four categories of scene images and four types of significant objects were designed as stimuli.
The advancements in image understanding have inspired computer vision researchers to develop computational systems capable of automatically recognizing the category of scenes.
To allow a straightforward comparison with state-of-the-art methods [6, 8 10] the proposed approach has been experimentally tested on a benchmark database of about 4000 images belonging to fifteen different basic categories of scene.
In the learning phase a model that represents the best distribution of the involved codewords in each category of scenes was built by using a learning algorithm based on Latent Dirichlet Allocation [35].
Dataset 3 is from [32] including 477 images in 9 categories of scenes: Country, Field, Forest, Indoor, Mountain, Oldbuilding, Street, Urban, Water.
The dataset involved in their experiments contained thirteen basic level categories of scenes: highway, inside of cities, tall buildings, streets, forest, coast, mountain, open country, suburb residence, bedroom, kitchen, living room, and office.
Images are grouped in fifteen basic categories of scenes (Figure 6): coast, forest, bedroom, kitchen, living room, suburban, office, open countries, mountains, tall building, store, industrial, inside city, and highway.
