Trends in retrieval system performance

Author(s):  
J. Zobel ◽  
H.E. Williams ◽  
S. Kimberley
Author(s):  
Chia-Hung Wei ◽  
Chang-Tsun Li ◽  
Yue Li

As distributed mammogram databases at hospitals and breast screening centers are connected together through PACS, a mammogram retrieval system is needed to help medical professionals locate the mammograms they want to aid in medical diagnosis. This chapter presents a complete content-based mammogram retrieval system, seeking images that are pathologically similar to a given example. In the mammogram retrieval system, the pathological characteristics that have been defined in Breast Imaging Reporting and Data System (BI-RADSTM) are used as criteria to measure the similarity of the mammograms. A detailed description of those mammographic features is provided in this chapter. Since the user’s subjective perception should be taken into account in the image retrieval task, a relevance feedback function is also developed to learn individual users’ knowledge to improve the system performance.


2014 ◽  
Vol 12 (4) ◽  
pp. 3373-3381
Author(s):  
Metty Mustikasari ◽  
Sarifuddin Madenda

Recently Content based image retrieval (CBIR) is an active research. This paper proposes a technique to retrieve images based on color feature and evaluate the retrieval system performance. In this retrieval system Euclidean distance and City block distance are used to measure similarity of images. This algorithm is tested by using Corel image database which is provided by James Wang.  The performance of retrieval system is measured in terms of its recall and precision.  The effectiveness of retrieval system is also measured based on Average Rank (AVRR) of all relevant retrieves images and Ideal Average Rank of relevant images (IAVRR). The experimental results show that city block has achieved higher retrieval performance than Euclidean distance.


2015 ◽  
Vol 1 (2) ◽  
pp. 163
Author(s):  
Frank Flórez Montes ◽  
Jhon Alexander Tabagorda Giraldo

ONTARE. REVISTA DE INVESTIGACIÓN DE LA FACULTAD DE INGENIERÍAEn este trabajo, se presentan los procesos de diseño y prototipado rápido de un controlado por etapas, para un brazo robótico de un sistema de búsqueda y recuperación automático (ASLRS) de libros para una biblioteca, denominado Biblio-bot. El controlador por etapas, se diseñó a través de reglas de decisión secuencial y combinacional basadas en máquinas de estado y diagramas de flujo del entorno de Simulink-Stateflow, el cual permite la generación automática de código de ejecución en tiempo real, además de la validación del diseño en entornos de realidad virtual. El artículo presenta los resultados del proyecto Biblio-bot relacionados con el diseño y puesta a punto del proceso de recuperación de libros por parte del brazo robótica, dado que es el proceso más crítico en el funcionamiento del sistema ABSTRACTIn  this  research  paper  we  present  the  design  and  rapid  prototyping processes  of a stage-based controller for a robotic arm in an automatic search and retrieval system (ASLRS) of books in a library, called Biblio-bot. The design of a stage-based controller uses  sequential and combinational decision rules based on state machines and flow charts of the Simulink­ State flow environment. This toolbox allows automatic code generation at real-time execution and validation of designs in virtual reality environments. We show outcomes of the Biblio-bot project concerning  the design and  tuning of books, recovery processes using the robotic arm. This process is the most critical task in the Biblio-bot system performance. 


2017 ◽  
Vol 94 (5-8) ◽  
pp. 1811-1824 ◽  
Author(s):  
Gianluca D’Antonio ◽  
Manuela De Maddis ◽  
Joel Sauza Bedolla ◽  
Paolo Chiabert ◽  
Franco Lombardi

Sign in / Sign up

Export Citation Format

Share Document