An adaptive segmentation method combining MSRCR and mean shift algorithm with K-means correction of green apples in natural environment

Sun, Sashuang; Song, Huaibo; He, Dongjian; Lu, Yan

doi:10.1016/j.inpa.2018.08.011

Cited by 24 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this paper, we showed the process and effect of the improved light enhancement fusion algorithm for pressure gauge image enhancement in Figure 5 . To further verify the effectiveness of the improved algorithm proposed in this paper, we compare the results with Contrast Limited Adaptive Histogram Equalization (CLAHE) [ 31 ], Dark Channel Defogging (HRDCP) [ 32 ], Multi-Scale Retinex with Color Restoration (MSRCR) [ 33 ], and MSRCR + gamma [ 34 ] in the same experimental environment.…”

Section: Resultsmentioning

confidence: 99%

A High-Precision Automatic Pointer Meter Reading System in Low-Light Environment

Shi

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

At present, pointer meters are still widely used because of their mechanical stability and electromagnetic immunity, and it is the main trend to use a computer vision-based automatic reading system to replace inefficient manual inspection. Many correction and recognition algorithms have been proposed for the problems of skew, distortion, and uneven illumination in the field-collected meter images. However, the current algorithms generally suffer from poor robustness, enormous training cost, inadequate compensation correction, and poor reading accuracy. This paper first designs a meter image skew-correction algorithm based on binary mask and improved Mask-RCNN for different types of pointer meters, which achieves high accuracy ellipse fitting and reduces the training cost by transfer learning. Furthermore, the low-light enhancement fusion algorithm based on improved Retinex and Fast Adaptive Bilateral Filtering (RBF) is proposed. Finally, the improved ResNet101 is proposed to extract needle features and perform directional regression to achieve fast and high-accuracy readings. The experimental results show that the proposed system in this paper has higher efficiency and better robustness in the image correction process in a complex environment and higher accuracy in the meter reading process.

show abstract

Section: Resultsmentioning

confidence: 99%

A High-Precision Automatic Pointer Meter Reading System in Low-Light Environment

Shi

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Los algoritmos de partición tratan de descubrir clúster reubicando iterativamente puntos entre subconjuntos. El algoritmo k-means según investigaciones realizadas por Sun et al (2019); Du (2019) y Joshi et al…”

Section: Análisis De Clúster Para Identificar Conglomerados De Invest...unclassified

Método de algoritmo de clúster para el análisis del perfil de investigadores científicos

Bárcenas

2022

e-Ciencias de la Información

View full text Add to dashboard Cite

El aumento de la producción científica convierte en un desafío la tarea de identificar patrones y rasgos particulares que caractericen a los investigadores. Lograr establecer niveles de compatibilidad y similaridad entre actores en un contexto de investigación científica a partir de sus perfiles requiere de un proceso rápido y apropiado. El objetivo de este artículo es evaluar los niveles de similaridad, distancia euclidiana y compatibilidad entre vectores de investigadores, a partir de algoritmos de agrupamiento, escalamiento multidimensional, principios del modelo espacio-vectorial y atributos de sus perfiles científicos, considerando las terminologías que se abordan en su producción científica. Se utilizaron métodos teóricos y empíricos, incluyendo técnicas y herramientas de minería de texto. La aplicación del procedimiento en el Centro de Estudios de la Energía y Tecnología Avanzada de Cuba (CEETAM) y la Universidad Técnica de Cotopaxi (UTC) en Ecuador, evidenció su efectividad. Como resultado se pudo identificar los profesionales con mayores niveles de coincidencia en áreas a fines y líneas de investigación, lo que propicia el establecimiento de Comunidades Colectivas de Conocimientos; se pudo demostrar que los métodos empleados pueden ser integrados a las TIC, resultando en la obtención de relaciones perceptuales entre los investigadores y expresando los grupos que se forman a partir de conglomerados de observaciones en cada subcategoría y dominios de conocimientos de los dos casos de estudio analizados.

show abstract

“…Many unnecessary calculations are performed, the time grows exponentially, and the search efficiency decreases [21]. Furthermore, images acquired through various channels are subject to a variety of random disturbances and conditions, resulting in a large amount of noise in the acquired original images, causing the features of things in the acquired original images to change dramatically, and if such images are analyzed directly, the understanding of the images will be greatly skewed [22]. As a result, optimizing the OTSU algorithm to increase computing efficiency and efficacy has become a challenging and contentious subject.…”

Section: Data Preparationmentioning

confidence: 99%

Predicting Difficulty Level of Surgical Removal of Impacted Mandibular Third Molar Using Deep Learning Approaches

Elborolosy

Salem

Hamed

et al. 2022

Preprint

View full text Add to dashboard Cite

This work presents three automated pre-trained models to predict the difficulty of extracting the mandibular third molar using a dataset of 2414 panoramic radiography images based on pre-processed (shifted and rotated) from left and right mandibular third molar instances. In this research, we employed the four distinct architectural models, namely VGG-16, VGG-19, MobileNetV2, and ResNet50 to identify the difficulty of removing a mandibular third molar. We categorized the dataset into four categories of complexity to help in categorization (Normal, Easy, Medium, and difficult). As a result, VGG-16, VGG-19, MobileNetV2 and ResNet50 had prediction accuracies of 81%, 82%, 79% and 44%, respectively. Findings affirmed that the proposed deep learning model using VGG-19 could be a good tool to predict the difficulty of extracting a mandibular third molar using a panoramic radiographic image.

show abstract

An adaptive segmentation method combining MSRCR and mean shift algorithm with K-means correction of green apples in natural environment

Cited by 24 publications

References 16 publications

A High-Precision Automatic Pointer Meter Reading System in Low-Light Environment

A High-Precision Automatic Pointer Meter Reading System in Low-Light Environment

Método de algoritmo de clúster para el análisis del perfil de investigadores científicos

Predicting Difficulty Level of Surgical Removal of Impacted Mandibular Third Molar Using Deep Learning Approaches

Contact Info

Product

Resources

About