Latifa Greche

ORCID: 0000-0002-3977-2855
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Face and Expression Recognition
  • Emotion and Mood Recognition
  • Face recognition and analysis
  • Remote Sensing in Agriculture
  • Spectroscopy and Chemometric Analyses
  • Leaf Properties and Growth Measurement
  • Smart Agriculture and AI
  • Neural Networks and Applications
  • Hand Gesture Recognition Systems
  • Image Retrieval and Classification Techniques

Rothamsted Research
2023-2024

Agence pour le Développement et la Réhabilitation de la Ville de Fès
2021

Sidi Mohamed Ben Abdellah University
2015-2017

Renewable Energy Systems (United States)
2017

National Agency for the Development of Renewable Energy and Energy Efficiency
2016

In this paper, we compare classification results, of six facial expressions including joy, surprise, sadness, anger, disgust, and fear, relying on two different methods distance computing between 121 landmark points the face. Facial features were computed using L1 norm (Manhattan distance) in first case L2 (Euclidean second case. Training test data have been collected kinect sensor. Labelled dataset contains sequences extracted from face each subject while displaying fear. Classification has...

10.1109/wits.2017.7934618 article EN 2017-04-01

Due to the adverse effect of prolonged drought stress on plants, accurate detection is essential for water use efficiency and maintaining productivity. Hyperspectral imaging frequently used non-invasive plant phenotyping, allowing long-term monitoring crop health due its sensitivity subtle changes in leaf constituents. The broad spectrum hyperspectral data enables development multiple vegetation indices (Vis) derived from different spectral regions estimate biophysical biochemical traits....

10.20944/preprints202407.1362.v1 preprint EN 2024-07-17

Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional methods perform well in homogenous environments, the performance decreases when used more complex environments. This study aimed to develop fast and robust neural-network-based tool phenotype plants both field glasshouse environments high-throughput manner. Digital images of cowpea (from glasshouse) wheat field) with different nutrient supplies across their full...

10.3390/plants12102035 article EN cc-by Plants 2023-05-19

Sustainable fertilizer management in precision agriculture is essential for both economic and environmental reasons. To effectively manage input, various methods are employed to monitor track plant nutrient status. One such method hyperspectral imaging, which has been on the rise recent times. It a remote sensing tool used physiological changes response conditions availability. However, conventional processing mainly focuses either spectral or spatial information of plants. This study aims...

10.3389/fpls.2023.1209500 article EN cc-by Frontiers in Plant Science 2023-10-16

Accurate detection of drought stress in plants is essential for water use efficiency and agricultural output. Hyperspectral imaging (HSI) provides a non-invasive method plant phenotyping, allowing the long-term monitoring health due to sensitivity subtle changes leaf constituents. The broad spectral range HSI enables development different vegetation indices (VIs) analyze trait responses multiple stresses, such as combination nutrient stresses. However, known VIs may underperform when...

10.3390/rs16183446 article EN cc-by Remote Sensing 2024-09-17

In this paper we built an automatic system for performance reviews of a new approach facial expression recognition FER which is essentially based on Histogram Oriented Gradient and Normalized Cross Correlation. The was evaluated by varying two parameters: face resolution colour space images. Results show that good can be attained using low resolution, in particular 64 pixels RGB

10.1109/it4od.2016.7479316 article EN 2016-03-01

In this paper an automatic system of performance review has been proposed for facial expression recognition issue. The is essentially based on histograms oriented gradient features and multi layer feed forward neural network. was evaluated three different dataset by varying two parameters: face resolution color space images. Results demonstrate that good rates can be obtained using small image in both spaces grayscale RGB.

10.1109/cadiag.2017.8075680 article EN 2017-01-01
Coming Soon ...