Project for Training and Extracting Local Quantized Pattern Feature
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Local Quantized Pattern

This is an implementation for Local Quantized Pattern feature which is very popular on the research of face recognition and object recognition.

What is LQP

LQP is a generalization of local pattern features(LBP) that makes use of vector quantization and lookup table to let local pattern features have many more pixels and/or quantization levels without sacrificing simplicity and computational efficiency. More information about LQP, please refer to

Visual Recognition using Local Quantized Patterns

Face Recognition using Local Quantized Patterns

The project is based on the Opencv library when dealing with the pixels.


Step 1: Generate Codebook of LQP based on the training data

bin/extractLQP jpglist codebookFile ClucenterFile -g

Step 2: Cluster

bin/KMeans codebookFile midResult ClucenterFile

step 3: Extract LQP Feature,LQP_feature is the output file.

bin/extractLQP JpgList LQP_feature ClucenterFile -e


Any bugs, feel free to contact me, or you have some ideas about improving the result. I am very grateful you have any recommendations.