Faster and optimal detection of parametric shapes

In this project, an analysis of the faster detection of shapes using Randomized Hough Transform (RHT) was investigated. Since reduced computational complexity and time efficiency are the major concerns for complex image analysis, the focus of the research was to investigate RHT for these specific tasks. Also, a detailed analysis of probability theory associated with RHT theory was investigated as well. Thus effectiveness of RHT was proven mathematically in this project. In this project, RHT technique combined with Generalized Hough Transform (GHT) using Newton's curve fitting technique was proposed for faster detection of shapes in the Hough Domain. Finally, the image under question was enhanced using Minimum Cross-Entropy Optimization to further enhance the image and then RGHT process was carried out. This helped the RGHT process to obtain the required time efficiency.

Faster and optimal detection of parametric shapes

In this project, an analysis of the faster detection of shapes using Randomized Hough Transform (RHT) was investigated. Since reduced computational complexity and time efficiency are the major concerns for complex image analysis, the focus of the research was to investigate RHT for these specific tasks. Also, a detailed analysis of probability theory associated with RHT theory was investigated as well. Thus effectiveness of RHT was proven mathematically in this project. In this project, RHT technique combined with Generalized Hough Transform (GHT) using Newton's curve fitting technique was proposed for faster detection of shapes in the Hough Domain. Finally, the image under question was enhanced using Minimum Cross-Entropy Optimization to further enhance the image and then RGHT process was carried out. This helped the RGHT process to obtain the required time efficiency.

A Comparative Study on the Center-based Iterative Hough Transform

Circle detection is one of the most critical aspects of computer vision and has been widely studied and developed in a variety of ways. The Center-based Iterative Hough Transform (CBIHT) is a method for unassisted multiple circle detection, based upon iterative uses of a center-based voting process to determine the circle’s center coordinate. This paper gives a thorough analysis of the CBIHT as well as a comparison with the Standard Hough Transform (SHT) and its well-known variants including the Generalized Hough Transform (GHT) and the Adaptive Hough Transform (AHT). When applied to synthetic and real-life circular images, our accuracy and performance comparison studies show that (i) the CBIHT is more computationally efficient than the SHT’s brute-force algorithm; (ii) the CBIHT’s center-based voting method has greater resilience to noise than the GHT and AHT’s gradient information method; and (iii) the CBIHT’s iterative process provides an adaptability and speed in unassisted multiple circle detection similar to that of the AHT; (iv) yet, the CBIHT requires no parameters for circle detection unlike the GHT and the AHT. All in all, a comparison with other methods highlights the aforementioned merit of the CBIHT, proving the CBIHT to be an excellent choice in detecting the circles with noise in real-life images.

MEG–MRI CO-REGISTRATION USING 3D GENERALIZED HOUGH TRANSFORM

In this paper, we propose a method to use the three-dimensional (3D) generalized Hough transform (GHT) to co-register magnetoencephalography (MEG) and magnetic resonance imaging (MRI) of a brain automatically, whose results can be used to align MRI images and MEG data accurately and efficiently. Recently, many medical devices have been developed to study the neuronal activity in the human brain. MEG is a high-temporal-resolution measurement tool to study the physiological functions of brain nerves noninvasively; whereas the MRI of the scalp, skull, and cortex of the human brain is a high-spatial-resolution tool. The proposed method combines two tools for investigating the cognitive neuroscience between the human brain structure and weak magnetic fields from two different medical systems. An accurate and automatic registration method is necessitated to improve the brain analysis processes by combining multimodal data. The conventional GHT is a well-known method for detecting two-dimensional (2D) images or locating transformed planar shapes in 2D image processes. To further improve the 2D GHT, we extended it to a 3D GHT, which can co-register MEG and MRI data automatically and accurately. Some experimental results are included to demonstrate and evaluate the error and applicability of MEG–MRI co-registration.

MAGNETOENCEPHALOGRAPHY–ELECTROENCEPHALOGRAPHY CO-REGISTRATION USING 3D GENERALIZED HOUGH TRANSFORM

This study proposes an advanced co-registration method for an integrated high temporal resolution electroencephalography (EEG) and magnetoencephalography (MEG) data. The MEG has a higher accuracy for source localization techniques and spatial resolution by sensing magnetic fields generated by the entire brain using multichannel superconducting quantum interference devices, whereas EEG can record electrical activities from larger cortical surface to detect epilepsy. However, by integrating the two modality tools, we can accurately localize the epileptic activity compared to other non-invasive modalities. Integrating the two modality tools is challenging and important. This study proposes a new algorithm using an extended three-dimensional generalized Hough transform (3D GHT) to co-register the two modality data. The pre-process steps require the locations of EEG electrodes, MEG sensors, head-shape points of subjects and fiducial landmarks. The conventional GHT algorithm is a well-known method used for identifying or locating two 2D images. This study proposes a new co-registration method that extends the 2D GHT algorithm to a 3D GHT algorithm that can automatically co-register 3D image data. It is important to study the prospective brain source activity in bio-signal analysis. Furthermore, the study examines the registration accuracy evaluation by calculating the root mean square of the Euclidean distance of MEG–EEG co-registration data. Several experimental results are used to show that the proposed method for co-registering the two modality data is accurate and efficient. The results demonstrate that the proposed method is feasible, sufficiently automatic, and fast for investigating brain source images.

AUTOMATIC CO-REGISTRATION OF MEG AND 3D DIGITIZATION USING 3D GENERALIZED HOUGH TRANSFORM

In this study, we propose a new automatic co-registration method for the coordinate systems of magnetoencephalography (MEG) data and third dimension digitizer (3D DIG) data of a head using the 3D generalized Hough transform (GHT) during image processing. The technique is important for the research of brain functionalities; it can be done automatically, and quickly combines data from functional brain mapping tools like MEG and DIG, etc. MEG is a measurement instrument used to noninvasively analyze the physiological activity of neurons with high temporal resolution, but it lacks the head-shape of subjects and head with respect to the MEG sensors. 3D DIG can record head- shape, facial features, and anatomical markers in a 3D coordinate system in real time. Thus, combining the two modalities is beneficial in correlating the obtained brain data with physiological activity. According to much of the research, the GHT is useful for recognizing or locating two 2D images. However, the GHT algorithm can be extended to the 3D GHT to automatically co-register the 3D data. In this study, we use the 3D GHT to co-register three subject datasets with MEG and 3D DIG data, and evaluate the average distance errors between the proposed method and the MEG160 system. Some of the experimental results demonstrate the applicability of the proposed 3D GHT accurately and efficiently.