scholarly journals Using ephemeral clustering and query logs to organize web image search results on mobile devices

2011 ◽  
Author(s):  
Jose G. Moreno ◽  
Gaël Dias
Keyword(s):  
Mobile Devices ◽  
Image Search ◽  
Search Results ◽  
Query Logs

Location Based E-commerce System

2011 ◽  
pp. 881-892
Author(s):  
Nuno André Osório Liberato ◽  
João Eduardo Quintela Alves de Sous Varajão ◽  
Emanuel Soares Peres Correia ◽  
Maximino Esteves Correia Bessa
Keyword(s):  
Mobile Devices ◽  
System Architecture ◽  
Mobile Applications ◽  
Service Providers ◽  
Smart Phones ◽  
Search Results ◽  
Desktop Computers ◽  
Product Search ◽  
Near Future ◽  
Potential Customers

Location-based mobile services (LBMS) are at present an ever growing trend, as found in the latest and most popular mobile applications launched. They are, indeed, supported by the hasty evolution of mobile devices capabilities, namely smart phones, which are becoming truer mobile pocket-computers; by users demand, always searching for new ways to benefit from technology, besides getting more contextualized and user-centred services; and, lastly, by market drive, which sees mobile devices as a dedicated way to reach customers, providing profile-based publicity, products, discounts and events. With e-commerce, products and services started arriving to potential customers through desktop computers, where they can be bought and fast delivered to a given address. However, expressions such as “being mobile”, “always connected”, “anytime anywhere” that already characterize life in the present will certainly continue to do so in the near future. Meanwhile, mobile devices centred commerce services seem to be the next step. Therefore, this paper presents a system architecture designed for location-based e-commerce systems. These systems, where location plays the most important role, enable a remote products/services search, based in user parameters: after a product search, shops with that products are returned in the search results and are displayed in a map, around the user present location; and services like obtaining more information, reserving and purchasing are made available as well. This concept represents a mix between traditional client-oriented commerce and faceless mass-oriented e-commerce, enabling a proximity-based user-contextualized system, being well capable of conveying significant advantages and facilities to both service-providers/retailers and users.

Visual diversification of image search results

2009 ◽  
Author(s):  
Reinier H. van Leuken ◽  
Lluis Garcia ◽  
Ximena Olivares ◽  
Roelof van Zwol
Keyword(s):  
Image Search ◽  
Search Results

scholarly journals Transfer Learning-Based Search Model for Hot Pepper Diseases and Pests

Agriculture ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 439 ◽  
Author(s):  
Helin Yin ◽  
Yeong Hyeon Gu ◽  
Chang-Jin Park ◽  
Jong-Han Park ◽  
Seong Joon Yoo
Keyword(s):  
Nearest Neighbor ◽  
Image Data ◽  
Performance Comparison ◽  
Classification Model ◽  
Search Model ◽  
Hot Pepper ◽  
Final Decision ◽  
Image Search ◽  
K Nearest Neighbor ◽  
Search Results

The use of conventional classification techniques to recognize diseases and pests can lead to an incorrect judgment on whether crops are diseased or not. Additionally, hot pepper diseases, such as “anthracnose” and “bacterial spot” can be erroneously judged, leading to incorrect disease recognition. To address these issues, multi-recognition methods, such as Google Cloud Vision, suggest multiple disease candidates and allow the user to make the final decision. Similarity-based image search techniques, along with multi-recognition, can also be used for this purpose. Content-based image retrieval techniques have been used in several conventional similarity-based image searches, using descriptors to extract features such as the image color and edge. In this study, we use eight pre-trained deep learning models (VGG16, VGG19, Resnet 50, etc.) to extract the deep features from images. We conducted experiments using 28,011 image data of 34 types of hot pepper diseases and pests. The search results for diseases and pests were similar to query images with deep features using the k-nearest neighbor method. In top-1 to top-5, when using the deep features based on the Resnet 50 model, we achieved recognition accuracies of approximately 88.38–93.88% for diseases and approximately 95.38–98.42% for pests. When using the deep features extracted from the VGG16 and VGG19 models, we recorded the second and third highest performances, respectively. In the top-10 results, when using the deep features extracted from the Resnet 50 model, we achieved accuracies of 85.6 and 93.62% for diseases and pests, respectively. As a result of performance comparison between the proposed method and the simple convolutional neural network (CNN) model, the proposed method recorded 8.62% higher accuracy in diseases and 14.86% higher in pests than the CNN classification model.

Sign in / Sign up

Export Citation Format

Share Document