scholarly journals Automatic Analysis of Bees’ Waggle Dance

2020 ◽  
Author(s):  
Jordan Reece ◽  
Margaret Couvillon ◽  
Christoph Grüter ◽  
Francis Ratnieks ◽  
Constantino Carlos Reyes-Aldasoro
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Background Subtraction ◽  
Time Frame ◽  
Waggle Dance ◽  
Automatic Analysis ◽  
Learning Techniques ◽  
Low Pass ◽  
Processing Steps ◽  
Traditional Image

AbstractThis work describe an algorithm for the automatic analysis of the waggle dance of honeybees. The algorithm analyses a video of a beehive with 13,624 frames, acquired at 25 frames/second. The algorithm employs the following traditional image processing steps: conversion to grayscale, low pass filtering, background subtraction, thresholding, tracking and clustering to detect run of bees that perform waggle dances. The algorithm detected 44,530 waggle events, i.e. one bee waggling in one time frame, which were then clustered into 511 waggle runs. Most of these were concentrated in one section of the hive. The accuracy of the tracking was 90% and a series of metrics like intra-dance variation in angle and duration were found to be consistent with literature. Whilst this algorithm was tested on a single video, the ideas and steps, which are simple as compared with Machine and Deep Learning techniques, should be attractive for researchers in this field who are not specialists in more complex techniques.

scholarly journals Combining Low-Level Image Features with Features from A Simple Convolutional Neural Network

2019 ◽  
pp. 136-139
Author(s):  
Ozge Oztimur Karadag ◽  
Ozlem Erdas
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Image Data ◽  
Image Features ◽  
Data Set ◽  
Low Level ◽  
Learning Techniques ◽  
Processing Techniques ◽  
Layered Architectures ◽  
Traditional Image

In the traditional image processing approaches, first low-level image features are extracted and then they are sent to a classifier or a recognizer for further processing. While the traditional image processing techniques employ this step-by-step approach, majority of the recent studies prefer layered architectures which both extract features and do the classification or recognition tasks. These architectures are referred as deep learning techniques and they are applicable if sufficient amount of labeled data is available and the minimum system requirements are met. Nevertheless, most of the time either the data is insufficient or the system sources are not enough. In this study, we experimented how it is still possible to obtain an effective visual representation by combining low-level visual features with features from a simple deep learning model. As a result, combinational features gave rise to 0.80 accuracy on the image data set while the performance of low-level features and deep learning features were 0.70 and 0.74 respectively.

scholarly journals The NoisyOffice Database: A Corpus To Train Supervised Machine Learning Filters For Image Processing

2019 ◽  
Vol 63 (11) ◽  
pp. 1658-1667
Author(s):  
M J Castro-Bleda ◽  
S España-Boquera ◽  
J Pastor-Pellicer ◽  
F Zamora-Martínez
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
Supervised Learning ◽  
Image Enhancement ◽  
Super Resolution ◽  
Supervised Machine Learning ◽  
Text Documents ◽  
Learning Techniques ◽  
Printed Text

Abstract This paper presents the ‘NoisyOffice’ database. It consists of images of printed text documents with noise mainly caused by uncleanliness from a generic office, such as coffee stains and footprints on documents or folded and wrinkled sheets with degraded printed text. This corpus is intended to train and evaluate supervised learning methods for cleaning, binarization and enhancement of noisy images of grayscale text documents. As an example, several experiments of image enhancement and binarization are presented by using deep learning techniques. Also, double-resolution images are also provided for testing super-resolution methods. The corpus is freely available at UCI Machine Learning Repository. Finally, a challenge organized by Kaggle Inc. to denoise images, using the database, is described in order to show its suitability for benchmarking of image processing systems.

Intelligent grading system based on deep learning

2021 ◽  
pp. 002072092098399
Author(s):  
Meng Xiao ◽  
Haibo Yi
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Secondary Schools ◽  
Image Recognition ◽  
Processing Method ◽  
Grading System ◽  
Recognition Method ◽  
Lightweight Framework ◽  
Examination Method ◽  
Learning Techniques

According to the survey, off-line examination is still the main examination method in universities, primary and secondary schools. The grading processing of off-line examination is time-consuming. Besides, since the off-line grading is subjective, it is error-prone. In order to address the challenges in off-line examinations of universities, primary and secondary schools, it is very urgent to improve the efficiency of off-line grading. In order to realize intelligent grading for off-line examinations, we exploit deep learning techniques to off-line grading. First, we propose an image processing method for English letters. Second, we propose a image recognition method based on deep learning for English letters. Third, we propose a lightweight framework for grading. Based on the above designs, we design an intelligent grading system based on deep learning. We implement the system and the result shows that the intelligent grading system can batch grading efficiently. Besides, compared with related designs, the proposed system is more flexible and intelligent.

Sign in / Sign up

Export Citation Format

Share Document