Automatic Feature Detection Research Articles

Automatic detection of temporomandibular joint osteoarthritis radiographic features using deep learning artificial intelligence. A Diagnostic accuracy study

ObjectiveThe purpose of this study was to investigate the diagnostic performance of a neural network Artificial Intelligence model for the radiographic confirmation of Temporomandibular Joint Osteoarthritis in reference to an experienced radiologist. Materials and MethodsThe diagnostic performance of an AI model in identifying radiographic features in patients with TMJ-OA was evaluated in a diagnostic accuracy cohort study. Adult patients elected for radiographic examination by the Diagnostic Criteria for Temporomandibular Disorders decision tree were included. Cone-beam computed Tomography images were evaluated by object detection YOLO deep learning model. The diagnostic performance was verified against examiner radiographic evaluation. ResultsThe differences between the AI model and examiner were non-significant statistically, except in the subcortical cyst (P=0.049*). AI model showed substantial to near-perfect levels of agreement when compared to those of the examiner data. Regarding each radiographic phenotype, the AI model reported favorable sensitivity, specificity, accuracy, and highly statistically significant Receiver Operating Characteristic (ROC) analysis (p < 0.001). Area Under Curve ranged from 0.872, for surface erosion, to 0.911 for subcortical cyst. ConclusionAI object detection model could open the horizon for a valid, automated, and convenient modality for TMJ-OA radiographic confirmation and radiomic features identification with a significant diagnostic power.

An Enhanced Multiscale Retinex, Oriented FAST and Rotated BRIEF (ORB), and Scale-Invariant Feature Transform (SIFT) Pipeline for Robust Key Point Matching in 3D Monitoring of Power Transmission Line Icing with Binocular Vision

Power transmission line icing (PTLI) poses significant threats to the reliability and safety of electrical power systems, particularly in cold regions. Accumulation of ice on power lines can lead to severe consequences, such as line breaks, tower collapses, and widespread power outages, resulting in economic losses and infrastructure damage. This study proposes an enhanced image processing pipeline to accurately detect and match key points in PTLI images for 3D monitoring of ice thickness using binocular vision. The pipeline integrates established techniques such as multiscale retinex (MSR), oriented FAST and rotated BRIEF (ORB) and scale-invariant feature transform (SIFT) algorithms, further refined with m-estimator sample consensus (MAGSAC)-based random sampling consensus (RANSAC) optimization. The image processing steps include automatic cropping, image enhancement, feature detection, and robust key point matching, all designed to operate in challenging environments with poor lighting and noise. Experiments demonstrate that the proposed method significantly improves key point matching accuracy and computational efficiency, reducing processing time to make it suitable for real-time applications. The effectiveness of the pipeline is validated through 3D ice thickness measurements, with results showing high precision and low error rates, making it a valuable tool for monitoring power transmission lines in harsh conditions.

What Should We Do With These? Challenges related to (semi-)automatically detected sites and features. A note

Recent advances in machine learning and computer vision techniques have brought (semi-)automatic feature detection within reach of an increasing number of archaeologists and archaeological institutions, including those in Finland. These techniques improve our ability to detect and gather information on archaeological cultural heritage over vast areas in a highly efficient manner. However, the widespread adoption of such methods can also pose significant challenges for archaeological cultural heritage management, especially in relation to certain types of near-ubiquitous archaeological remains from the 17th-20th centuries.

Artificial Intelligence based real-time automatic detection and classification of skin lesion in dermoscopic samples using DenseNet-169 architecture

The most common challenge faced by dermoscopy images is the automatic detection of lesion features. All the existing solutions focus on complex algorithms to provide accurate detections. In this research work, proposed Online Tigerclaw Fuzzy Region Segmentation with Deep Learning Classification model, an intellectual model is proposed that provides discrimination of features with classification even in fine-grained samples. This model works on four different stages, which include the Boosted Anisotropic Diffusion filter with Recursive Pixel Histogram Equalization (BADF-RPHE) in the preprocessing stage. The next step is the proposed Online Tigerclaw Fuzzy Region Segmentation (OTFRS) algorithm for lesion area segmentation of dermoscopic images, which can achieve 98.9% and 97.4% accuracy for benign and malignant lesions, respectively. In the proposed OTFRS, an accuracy improvement of 1.4% is achieved when compared with previous methods. Finally, the increased robustness of lesion classification is achieved using Deep Learning Classification –DenseNet 169 with 500 images. The proposed approach was evaluated with accuracy classifications of 100% and 98.86% for benign and malignant lesions, respectively, and a processing time of less than 18 sec. In the proposed DensetNet-169 classification technique, an accuracy improvement of 3% is achieved when compared with other state-of-art methods. A higher range of true positive values is obtained for the Region of Convergence (ROC) curve, which indicates that the proposed work ensures better performance in clinical diagnosis for accurate feature visualization analysis. The methodology has been validated to prove its effectiveness and throw light on the lives of affected patients so they can resume normalcy and live long. The research work was tested in real-time clinical samples, which delivered promising and encouraging results in skin cell detection procedures.

Application of Pattern Recognition and Computer Vision Tools to Improve the Morphological Analysis of Microplastic Items in Biological Samples.

Since, in many routine analytical laboratories, a stereomicroscope coupled with a digital camera is not equipped with advanced software enabling automatic detection of features of observed objects, in the present study, a procedure of feature detection using open-source software was proposed and validated. Within the framework of applying microscopic expertise coupled with image analysis, a set of digital images of microplastic (MP) items identified in organs of fish was used to determine shape descriptors (such as length, width, item area, etc.). The edge points required to compute shape characteristics were set manually in digital images acquired by the camera coupled with a binocular, and respective values were computed via the use of built-in MotiConnect software. As an alternative, a new approach consisting of digital image thresholding, binarization, the use of connected-component labeling, and the computation of shape descriptors on a pixel level via using the functions available in an OpenCV library or self-written in C++ was proposed. Overall, 74.4% of the images were suitable for thresholding without any additional pretreatment. A significant correlation was obtained between the shape descriptors computed by the software and computed using the proposed approach. The range of correlation coefficients at a very high level of significance, according to the pair of correlated measures, was higher than 0.69. The length of fibers can be satisfactorily approximated using a value of half the length of the outer perimeter (r higher than 0.75). Compactness and circularity significantly differ for particles and fibers.

Deep Learning-assisted Retinopathy of Prematurity (ROP) Screening

Retinopathy of prematurity (ROP) is a leading cause of blindness in premature infants worldwide, particularly in developing countries. In this research, we propose a Deep Convolutional Neural Network (DCNN) and image processing-based approach for the automatic detection of retinal features, including the optical disc (OD) and retinal blood vessels (BV), as well as disease classification using a rule-based method for ROP patients. Our DCNN model uses YOLO-v5 for OD detection and either Pix2Pix or a U-Net for BV segmentation. We trained our DCNN models on publicly available fundus image datasets of size 1,117 and 288 for OD detection and BV segmentation, respectively. We evaluated our approach on a dataset of 439 preterm neonatal retinal images, testing for ROP Zone and 6 BV masks. Our proposed system achieved excellent results, with the OD detection module achieving an overall accuracy of 98.94% (when IoU 0.5) and the BV segmentation module achieving an accuracy of 96.69% and a Dice coefficient between 0.60 and 0.64. Moreover, our system accurately diagnosed ROP in Zone-1 with 88.23% accuracy. Our approach offers a promising solution for accurate ROP screening and diagnosis, particularly in low-resource settings, where it has the potential to improve healthcare outcomes.

Automatic Localization of Five Relevant Dermoscopic Structures Based on YOLOv8 for Diagnosis Improvement.

The automatic detection of dermoscopic features is a task that provides the specialists with an image with indications about the different patterns present in it. This information can help them fully understand the image and improve their decisions. However, the automatic analysis of dermoscopic features can be a difficult task because of their small size. Some work was performed in this area, but the results can be improved. The objective of this work is to improve the precision of the automatic detection of dermoscopic features. To achieve this goal, an algorithm named yolo-dermoscopic-features is proposed. The algorithm consists of four points: (i) generate annotations in the JSON format for supervised learning of the model; (ii) propose a model based on the latest version of Yolo; (iii) pre-train the model for the segmentation of skin lesions; (iv) train five models for the five dermoscopic features. The experiments are performed on the ISIC 2018 task2 dataset. After training, the model is evaluated and compared to the performance of two methods. The proposed method allows us to reach average performances of 0.9758, 0.954, 0.9724, 0.938, and 0.9692, respectively, for the Dice similarity coefficient, Jaccard similarity coefficient, precision, recall, and average precision. Furthermore, comparing to other methods, the proposed method reaches a better Jaccard similarity coefficient of 0.954 and, thus, presents the best similarity with the annotations made by specialists. This method can also be used to automatically annotate images and, therefore, can be a solution to the lack of features annotation in the dataset.

Automated Audio Analysis of Dysarthria in Huntington’s disease (Audio-HD) (S37.010)

<h3>Objective:</h3> Using an exploratory approach, our goals were 1) identify features of speech that differentiated HD from controls, 2) use key speech features to train a classifier model and 3) compare these results to clinical assessments. <h3>Background:</h3> The diagnosis of Huntington’s disease (HD) is based primarily on the motor exam component of the Unified Huntington’s Disease Rating Scale (UHDRSTM). The UHDRSTM grades dysarthria from 0–4 (normal to anarthria), however automated speech feature detection could capture subtle changes that might serve as early disease biomarkers. <h3>Design/Methods:</h3> HD participants (n=46) and healthy controls (HC) (n=32) were matched for sex, age, and education. Participants were recorded during an 8 minute tablet-based protocol (Audio-HD) that included open-ended questions, passage reading, narrative prompt, picture description, and audio recording of the Stroop Color and Word Test (SCWT). Audio data underwent automated feature detection by Canary Speech after which key features were selected and used to train a classifier model. Model performance was compared to clinical assessment. <h3>Results:</h3> HD average UHDRSTM total motor score was 16.1 (SD=15.72) and CAG repeat length 43.1 (SD=3.62). Welch’s t-test (95% CI) identified &gt;1000 features of speech that differentiated HD from HC. The 20 most significant features were entered into a Random Forest classifier to generate a trained model. Classifier accuracy (HD vs. HC) was 96% (91% sensitivity, 98% specificity) and sensitivity was 96% for detecting dysarthria in HD. Interestingly, the model also correctly labeled 40% of HD cases lacking clinical dysarthria, suggesting it was capturing speech changes not apparent to the examiner. <h3>Conclusions:</h3> Audio-HD protocol using Canary Speech has significant potential as an efficient and sensitive tool for identifying speech biomarkers in HD. Further training of the model and longitudinal follow up will be critical for determining the overall utility of this approach. <b>Disclosure:</b> Mr. Sierra has nothing to disclose. Miss Hildebrand has nothing to disclose. Miss Ullman has nothing to disclose. Miss Mwangi has nothing to disclose. Mr. O’Connell has received personal compensation for serving as an employee of Canary Speech, Inc. Dr. Frank has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Novartis. Dr. Frank has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Sage Therapeutics. Dr. Frank has received personal compensation in the range of $500-$4,999 for serving as a Consultant for uniQure. The institution of Dr. Frank has received research support from Huntington’s Disease Society of America. The institution of Dr. Frank has received research support from Roche/Genentech. The institution of Dr. Frank has received research support from CHDI Foundation. The institution of Dr. Frank has received research support from Huntington Study Group. The institution of Dr. Frank has received research support from Triplet Therapeutics. Dr. Laganiere has received research support from HDSA.

Mapping floods from remote sensing data and quantifying the effects of surface obstruction by clouds and vegetation

Floods are one of the most devastating natural calamities affecting millions of people and causing damage all around the globe. Flood models and remote sensing imagery are often used to predict and understand flooding. An increasing number of earth observation satellites are producing data at a rate that far outpaces our ability to manually extract meaningful information from it, motivating a surge in research on automatic feature detection in satellite imagery using machine learning and deep learning algorithms to automate flood mapping so that information from large streams of data can be extracted in near-real time and used for disaster response at landscape scale. The development of such an algorithm is predicated on exposure to training datasets that are representative of the full range of diversity in the spatial and spectral signature of surface water as it is sampled by space-based instruments. To address these needs, we developed a semantically labeled dataset of high-resolution multispectral imagery (Maxar WorldView 2/3) strategically sampled to be representative of North American surface water variability along five spatiotemporal strata: latitude, topographic complexity, land use, and day of year. This dataset was utilized to train a convolutional neural network (CNN) to automatically detect inundation extents using the Deep Earth Learning, Tools, and Analysis (DELTA) framework, an open source TensorFlow/Keras interpreter for satellite imagery. Our research objective was to demonstrate the out-of-sample accuracy of our trained CNN at landscape scale. The model performed well, with 98% precision and 94% recall for the water class during validation. We then evaluated the accuracy of our satellite-derived flood maps from trained machine learning model against a hydraulic model. For this, we compared predicted inundation extents against the USGS Flood Inundation Mapping (FIM) Program's flood map library at 17 different locations, where the FIM library provides flood inundation extents based on hydraulic models built for river reaches and corresponding to stage measurements at a nearby USGS gaging site. Compared to the hydraulic model, we estimated the underprediction of flood inundation by optical remote sensing data in our areas of interest to be 62%. We used land use data from National Land Cover Database (NLCD) and cloud masks to estimate that 79% of underprediction was due to these obstructions, with 74% belonging to vegetation, 9% to clouds, and 4% to both. A significant amount of inundation is missed when only optical remote sensing data is considered, and we suggest the use of flood models along with remote sensing data for getting the most realistic flood inundation extents.

Assessment of shape-based features ability to predict the ascending aortic aneurysm growth.

The current guidelines for the ascending aortic aneurysm (AsAA) treatment recommend surgery mainly according to the maximum diameter assessment. This criterion has already proven to be often inefficient in identifying patients at high risk of aneurysm growth and rupture. In this study, we propose a method to compute a set of local shape features that, in addition to the maximum diameter D, are intended to improve the classification performances for the ascending aortic aneurysm growth risk assessment. Apart from D, these are the ratio DCR between D and the length of the ascending aorta centerline, the ratio EILR between the length of the external and the internal lines and the tortuosity T. 50 patients with two 3D acquisitions at least 6 months apart were segmented and the growth rate (GR) with the shape features related to the first exam computed. The correlation between them has been investigated. After, the dataset was divided into two classes according to the growth rate value. We used six different classifiers with input data exclusively from the first exam to predict the class to which each patient belonged. A first classification was performed using only D and a second with all the shape features together. The performances have been evaluated by computing accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUROC) and positive (negative) likelihood ratio LHR+ (LHR-). A positive correlation was observed between growth rate and DCR (r = 0.511, p = 1.3e-4) and between GR and EILR (r = 0.472, p = 2.7e-4). Overall, the classifiers based on the four metrics outperformed the same ones based only on D. Among the diameter-based classifiers, k-nearest neighbours (KNN) reported the best accuracy (86%), sensitivity (55.6%), AUROC (0.74), LHR+ (7.62) and LHR- (0.48). Concerning the classifiers based on the four shape features, we obtained the best accuracy (94%), sensitivity (66.7%), specificity (100%), AUROC (0.94), LHR+ (+∞) and LHR- (0.33) with support vector machine (SVM). This demonstrates how automatic shape features detection combined with risk classification criteria could be crucial in planning the follow-up of patients with ascending aortic aneurysm and in predicting the possible dangerous progression of the disease.

A deep learning and full consistency approach to roadway safety scoring

The World Health Organization (WHO) estimated that worldwide road traffic crashes account for 1.35 million annual deaths in 2018. Most studies in road safety field have focused on studying road features effect on crash frequency and injury severity. However, limited studies use automatic road features detection methods to evaluate road safety. This research applies deep learning object detection to automatically identify roads features and Full Consistency Method (FUCOM) to rank the effect of road features on safety. A deep artificial network object detector is trained to efficiently detect road objects in a front-facing camera image, then FUCOM is applied to determine safety weights for ten Key Safety Indicators (KSIs). After determining final weights, the proposed approach is applied on a case study in Greater Cairo, in which 354 km of multi-class roads are divided to 1-km sections and assigned a road safety score (RSS). The resulting RSS identifies areas that exhibit low safety scores, enabling decision makers to focus their efforts on features that can attain highest improvement. This research contributes to supporting governments and roadway asset management agencies in prioritizing their efforts (and funding) in addressing roadway safety – especially where structured historical data collection programs are largely missing.

Recent advances in automatic feature detection and classification of fruits including with a special emphasis on Watermelon (Citrillus lanatus): A review

This document provides an overview of advances in the task of automatic feature detection and classification of fruits, with and special interest in watermelon (Citrillus lanatus). The review was written with the objective to highlight the wealth of knowledge that exist in the application of analytical, smart and sensing image recognition techniques commonly used in agro-industry, and the computational approaches used to make the classification possible. Also, an specific interest is put in the contributions made in the development of automatic recognition systems geared towards for watermelon using images, acoustic and spectroscopy methodologies. The importance of this document is that it provides a conceptual summary of the methods for the automatic recognition of fruits, including machine learning and evolutionary computational algorithms to analyze their sensed data. In conclusion this is a first step into recognizing the challenges and opportunities that can be addressed in this field to augment the visibility of these methods and to further modernize the agro-industrial sector.

Early detection of breast cancer in mammograms using the lightweight modification of efficientNet B3

Breast cancer is one of the leading causes of death in women worldwide and early detection is critical to improving survival rates. In this study, we present a modified deep learning method for automatic feature detection for breast mass classification on mammograms. We propose to use EfficientNet, a Convolutional Neural Network (CNN) architecture that requires minimal parameters. The main advantage of EfficientNet is the small number of parameters, which allows efficient and accurate classification of mammogram images. Our experiments show that EfficientNet, with an overall accuracy of 86.5%, has the potential to be the fundamental for a fully automated and effective breast cancer detection system in the future. Our results demonstrate the potential of EfficientNet to improve the accuracy and efficiency of breast cancer detection compared to other approaches.

StreetScouting: A Deep Learning Platform for Automatic Detection and Geotagging of Urban Features from Street-Level Images

Urban environments are evolving rapidly in big cities; keeping track of these changes is becoming harder. Information regarding urban features, such as the number of trees, lights, or shops in a particular region, can be crucial for tasks, such as urban planning, commercial campaigns, or inferring various social indicators. StreetScouting is a platform that aims to automate the process of detecting, visualizing, and exporting the urban features of a particular region. Recently, the advent of deep learning has revolutionized the way many computer vision tasks are tackled. In this work, we present StreetScouting, an extensible platform for the automatic detection of particular urban features of interest. StreetScouting utilizes several state-of-the-art computer vision approaches including Cascade R-CNN and RetinaFace architectures for object detection, the ByteTrack method for object tracking, DNET architecture for depth estimation, and DeepLabv3+ architecture for semantic segmentation. As a result, the platform is able to detect and geotag urban features from visual data. The extracted information can be utilized by many commercial or public organizations, eliminating the need for manual inspection.

Research on Fingerprint Security Based on Improved Yolo Algorithm

The quantitative identification technology based on the statistical law of fingerprint features has become a new research difficulty and focus, and the automatic detection and classification of fingerprint features are the basis for realizing automatic fingerprint feature statistics. In this paper, a YOLO-based fingerprint feature detection method was proposed. First, a fingerprint feature dataset was established, which contained a total of 4,000 annotated fingerprint images; then, according to the characteristics of small size and dense distribution of fingerprint feature points, the YOLO network structure was improved, the original large target feature detection layer by 32-fold downsampling was deleted, and a new small feature fusion layer was added; the FPN, PAN, and SPP structures were used to achieve local and global feature extraction through multiple-scale fusion methods; finally, the SE channel attention mechanism module was added to effectively enhance the model robustness and detection ability of dense small objects. The experimental results show that compared with the improved FP-YOLO model of the original model, when the detection speed is basically unchanged, the mAP0.5 value is increased from 93.0% to 97.4%, and the weight is reduced by 3/4.

Automatic Roadside Feature Detection Based on Lidar Road Cross Section Images.

The United Nations (UN) stated that all new roads and 75% of travel time on roads must be 3+ star standard by 2030. The number of stars is determined by the International Road Assessment Program (iRAP) star rating module. It is based on 64 attributes for each road. In this paper, a framework for highly accurate and fully automatic determination of two attributes is proposed: roadside severity-object and roadside severity-distance. The framework integrates mobile Lidar point clouds with deep learning-based object detection on road cross-section images. The You Only Look Once (YOLO) network was used for object detection. Lidar data were collected by vehicle-mounted mobile Lidar for all Croatian highways. Point clouds were collected in .las format and cropped to 10 m-long segments align vehicle path. To determine both attributes, it was necessary to detect the road with high accuracy, then roadside severity-distance was determined with respect to the edge of the detected road. Each segment is finally classified into one of 13 roadside severity object classes and one of four roadside severity-distance classes. The overall accuracy of the roadside severity-object classification is 85.1%, while for the distance attribute it is 85.6%. The best average precision is achieved for safety barrier concrete class (0.98), while the worst AP is achieved for rockface class (0.72).

Computed Tomography as a Tool for Quantification and Classification of Roundwood—Case Study

The first goal of this paper is to verify the accuracy of four calculation methods of log volume. The tool to achieve this goal is to compare the results of the calculation of the log volume with the real log volume obtained from the three-dimensional reconstruction obtained by computed tomography. The second goal of this paper is to determine the effectiveness of displaying the qualitative features of wood in three-dimensional models of selected pieces of logs of oak, beech, and spruce, which were obtained using computed tomography. It is possible to state that each of the tested calculation methods of wood log volume are applicable in practice. The tested methods achieve excellent accuracy in determining the volume of spruce logs with a small variance of values, and conversely, in the case of beech wood, the tested methods are the most inaccurate with the largest variance of values. When determining the volume of wood logs, we recommend using the calculation method STN 48 0009, because it achieves the best results. Qualitative analysis based on CT scans of internal features can be described as a completely new level of approach to the evaluation of log quality. The performed analysis showed great potential for automatic detection of internal qualitative features in the tested spruce log. In this wood, wood defects are distinguishable by computed tomography. In the case of deciduous oak and beech, the situation is more complicated. The internal structure of these trees overlaps the internal qualitative features of the wood. To accurately detect internal errors in these trees, it will be necessary to perform many comparative tests to achieve optimal results.

Automatic Detection of Image-Based Features for Immunosuppressive Therapy Response Prediction in Oral Lichen Planus.

Oral lichen planus (OLP) is a chronic inflammatory disease, and the common management focuses on controlling inflammation with immunosuppressive therapy. While the response to the immunosuppressive therapy is heterogeneous, exploring the mechanism and prediction of the response gain greater importance. Here, we developed a workflow for prediction of immunosuppressive therapy response prediction in OLP, which could automatically acquire image-based features. First, 38 features were acquired from 208 OLP pathological images, and 6 features were subsequently obtained which had a significant impact on the effect of OLP immunosuppressive therapy. By observing microscopic structure and integrated with the corresponding transcriptome, the biological implications of the 6 features were uncovered. Though the pathway enrichment analysis, three image-based features which advantageous to therapy indicated the different lymphocytes infiltration, and the other three image-based features which bad for therapy respectively indicated the nicotinamide adenine dinucleotide (NADH) metabolic pathway, response to potassium ion pathway and adenosine monophosphate (AMP) activated protein kinase pathway. In addition, prediction models for the response to immunosuppressive therapy, were constructed with above image-based features. The best performance prediction model built by logistic regression showed an accuracy of 90% and the area under the receiver operating characteristic curve (AUROC) reached 0.947. This study provided a novel approach to automatically obtain biological meaningful image-based features from unannotated pathological images, which could indicate the immunosuppressive therapy in OLP. Besides, the novel and accurate prediction model may be useful for the OLP clinical management.

CNN-BASED TEMPLATE MATCHING FOR DETECTING FEATURES FROM HISTORICAL MAPS

Abstract. Efficiently detecting features from historical maps is a challenging task due to its inconsistent manual scribbling styles and the lack of large scale labelled training data. To tackle this issue, this paper proposes an automatic feature detection pipeline utilizing CNN-based template matching (TM), which can lead to efficient feature extraction with minimal input, i.e. one single template. Three CNN-based TM models equipped with different feature extractors are investigated and compared in this research, namely pre-trained VGG19 CNNs, autoencoders, and the combination of both. Experiments conducted on six tiles of the Swiss Old National Map demonstrate that the combined architecture achieves the best result in wetlands detection, resulting in a mean intersection over union (IoU) of 69% and an average F1 measure of 82%.

Lamb wave mode spectroscopy on complex structures with amplitude-based feature detection

The need for fast and effective Non-Destructive Testing (NDT) techniques is ever present. Existing techniques such as ultrasonic testing, whilst established and reliable, face many limitations when considering large structures such as those found in the aerospace and green energy sectors. Wave mode, as well as other wavenumber based filtering techniques have been presented to address many of these limitations. This work describes a novel application of Wave Mode Spectroscopy (WMS) along with feature detection for complex geometric shapes. The specimen's geometry is found during the wavefields measurement through the use of a 3D Scanning Laser Doppler Vibrometer (SLDV) allowing the wavefield to be mapped to a 2D plane with limited distortion of the wavelength and without any prior knowledge of the part's geometry. This was shown to allow WMS to be applied to continuous, multi-frequency wavefields and generate accurate thickness maps. Monogenic signal analysis has been applied to the same measurement data to generate amplitude maps that allow the automatic detection of edge features through the use of a Canny edge detection algorithm.