Search

Edge detection plays an important role in computer vision to extract object boundary. Multiscale edge detection method provides a variety of image features by different resolution at multiscale of edges. The method extracts coarse and fine structure edges simultaneously in an image. Due to this, the multiscale method enables more reliable edges are detected. Most of the multiscale methods are not translation invariant due to the decimated process. They mostly depend on the corresponding transform coefficients. These methods need more computation and a larger storage space. This study proposes a multiscale method that uses an average filter to smooth image at three different scales. Three different classical edge detectors namely Prewitt, Sobel and Laplacian were used to extract the edges from the smooth images. The edges extracted from the different scales of smooth images were then combined to form the multiscale edge detection. The performances of the multiscale images extracted from the three classical edge detectors were then compared and discussed.

Maintaining the quality of the water quality is one of the important aspects that play a substantial effect on the aquaculture industry especially in the tilapia industry. The quality of the water needs to be continuously monitored as any deviation from the allowed critical parameters such as water temperature and potential of hydrogen (pH) can cause unwanted scenarios such as disease, stress, higher mortality rate and profit loss. Currently, the monitoring process adopted by most fish breeders is done manually by using a portable sensor. This approach is found to be very tedious, ineffective use of manpower and time consuming particularly for the large-scale aquaculture industry. Hence, this research focuses on developing a simple, low-cost automated water quality monitoring system for the tilapia industry via LabVIEW software. The developed system will be able to monitor the parameter in real-time continuously with the capability of record and analyze each reading in a more efficient way. A data acquisition (DAQ) of NI myRIO-1900 is used as an interface between sensors and a monitoring station equipped with LabVIEW. Additionally, the developed system is equipped with an alarm system to alert the user when any deviation of the parameters occurs. Result shows that the system has a small range of average relative error of 4.28% and 6.22% for temperature and pH level respectively as compare to the portable sensor. Note that the errors are down to the selection of sensors. Furthermore, the developed prototype of the monitoring system has advantages in terms of its flexibility in extending the system with more sensors and allows a longer period of data collection without human intervention. The system is also upgradable with the integration of a control element to control the parameter when the monitored parameter is exceeded the threshold value. Succinctly, the system offers lots of advantages to the aquaculture industries with further improvement leads to better performance.