A Feature Learning and Object Recognition Framework for Underwater Fish Images

ABSTRACT:

Live fish recognition is one of the most crucial elements of fisheries survey applications where the vast amount of data is rapidly acquired. Different from general scenarios, challenges to underwater image recognition are posted by poor image quality, uncontrolled objects and environment, and difficulty in acquiring representative samples. In addition, most existing feature extraction techniques are hindered from automation due to involving human supervision. Toward this end, we propose an underwater fish recognition framework that consists of a fully unsupervised feature learning technique and an error-resilient classifier. Object parts are initialized based on saliency and relaxation labeling to match object parts correctly. A non-rigid part model is then learned based on fitness, separation, and discrimination criteria. For the classifier, an unsupervised clustering approach generates a binary class hierarchy, where each node is a classifier. To exploit information from ambiguous images, the notion of partial classification is introduced to assign coarse labels by optimizing the benefit of indecision made by the classifier. Experiments show that the proposed framework achieves high accuracy on both public and self-collected underwater fish images with high uncertainty and class imbalance.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

• While object recognition in various contexts has been well investigated in image processing and computer vision communities, there exist fundamental challenges to identifying live fish in an unconstrained natural habitat. Like most underwater imagery scenarios, one challenge is posted by the low image quality caused by fast attenuation of light in the water, poor control over illumination, the ubiquitous organic debris, etc. While capturing images for freely-swimming fish, there is a high uncertainty in many of the data due to low image quality, non-lateral fish views or curved body shapes.

DISADVANTAGES OF EXISTING SYSTEM:

• Above informations are seriously degrades the recognition performance since some critical information may be lost. Even without uncertainty, fish share a strong visual correlation among species. Common image features for object recognition are usually not sufficiently discriminative in this case.

PROPOSED SYSTEM:

In this paper, we propose a novel feature learning and object recognition framework. One advantage of the proposed framework is that it uses fully unsupervised algorithms to learn the features and class correlation, and thus provides an automatic solution for practical recognition systems. Specifically, the contributions of this paper include:

• A novel non-rigid part model that represents both appearance and geometric attributes of the fish body.

• An unsupervised learning algorithm of non-rigid part model based on systematic part initialization and an expectation-maximization-like (EM-like) alternating optimization algorithm.

• A novel hierarchical partial classification that successfully handles data uncertainty and class imbalance.

• A formal approach that determines the decision criteria based on an optimization formulation.

ADVANTAGES OF PROPOSED SYSTEM:

• Experimental results show a favorable performance of fish recognition on both large-scale public dataset and practical highly-uncertain dataset of live fish.

MODULES:

1. Image Acquisition

2. Preprocessing

3. Fish Detection

4. Feature Extraction

MODULE DESCRIPTION:

1. Image Acquisition:

• Image acquisition in image processing can be broadly defined as the action of retrieving an image from some source, usually a hardware-based source, so it can be passed through whatever processes need to occur afterward.

• Performing image acquisition in image processing is always the first step in the workflow sequence because, without an image, no processing is possible. The image that is acquired is completely unprocessed and is the result of whatever hardware was used to generate it, which can be very important in some fields to have a consistent baseline from which to work.

2.Preprocessing:

The aim of pre-processing is an improvement of the image data that suppresses unwanted distortions or enhances some image features important for further processing.

Image enhancement technique,

1. Local Laplacian Filters

1. Local Laplacian Filters:

In this stage, underwater images are enhanced by local Laplacian filter. LLF is used for edge-aware processing. In this underwater fish images are enhanced by preserving edges using LLF.

We characterize edges with a simple threshold on pixel values that allow us to differentiate large-scale edges from small-scale details. Building upon this result, we propose a set of image filters to achieve edge-preserving smoothing, detail enhancement, tone mapping, and inverse tone mapping.

3. Fish Detection:

After complete the preprocessing, fish detection is performed. Underwater fish detection is done by saliency map. Saliency map is used for object detection.

4. Feature Extraction and Recognition:

In this stage, recognition is done by SURF features. SURF features are used for extract the features from detected fish, using this features fishes are recognized in underwater by distance function.

SURF:

• SURF (Speeded-Up Robust Feature) is a speeded up version of SIFT, which is computationally efficient and very fast.

• SURF is a local robust feature detector which is used in object detection tasks.

• SURF is used to

  • Detect key points of an image

  • Assign orientation to each keypoint to achieve rotation invariance.

  • Assign descriptor to each key point

  • Match the keypoints between two images using nearest neighbour method

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System            : Pentium Dual Core.

• Hard Disk       : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB

• Tool                      : MATLAB R2013A

REFERENCE:

Meng-Che Chuang, Jenq-Neng Hwang, Fellow, IEEE, and Kresimir Williams, “A Feature Learning and Object Recognition Framework for Underwater Fish Images”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 25, NO. 4, APRIL 2016.