Similar & Duplicate Image Detection

#include <jni.h>
#include <string>
#include <vector>
#include <functional>
#include <opencv2/opencv.hpp>

// 1. 计算图片的 aHash (64位整数)
uint64_t computeHash(const cv::Mat& img) {
if (img.empty()) return 0;
cv::Mat resized, gray;
// 极速降采样至 8x8 并转灰度
cv::resize(img, resized, cv::Size(8, 8));
cv::cvtColor(resized, gray, cv::COLOR_BGR2GRAY);
cv::Scalar mean = cv::mean(gray);
uint64_t hash = 0;
int index = 0;
for (int i = 0; i < gray.rows; i++) {
for (int j = 0; j < gray.cols; j++) {
if (gray.at<uchar>(i, j) >= mean[0]) {
hash |= (1ULL << index);
}
index++;
}
}
return hash;
}

extern "C" JNIEXPORT jintArray JNICALL
Java_com_wefamily_papa_utils_OpenCVUtils_groupSimilarImages( 
JNIEnv* env, jobject /* this */, jobjectArray imagePaths, jint threshold) {

int n = env->GetArrayLength(imagePaths);
std::vector<uint64_t> hashes(n);

// 2. 依次读取图片并提取特征 (规避 OOM)
for (int i = 0; i < n; i++) {
jstring jpath = (jstring) env->GetObjectArrayElement(imagePaths, i);
const char* path = env->GetStringUTFChars(jpath, nullptr);
cv::Mat img = cv::imread(path, cv::IMREAD_COLOR);
hashes[i] = computeHash(img);
env->ReleaseStringUTFChars(jpath, path);
env->DeleteLocalRef(jpath);
}

// 3. 初始化并查集 (DSU) 进行聚类
std::vector<int> labels(n);
for(int i = 0; i < n; i++) labels[i] = i;

std::function<int(int)> find = [&](int i) {
return labels[i] == i ? i : (labels[i] = find(labels[i]));
};

// 4. 两两比对汉明距离，相似则合并分组
for(int i = 0; i < n; i++) {
for(int j = i + 1; j < n; j++) {
if (hashes[i] == 0 || hashes[j] == 0) continue;
int distance = __builtin_popcountll(hashes[i] ^ hashes[j]);
if (distance <= threshold) {
int rootI = find(i);
int rootJ = find(j);
if (rootI != rootJ) labels[rootI] = rootJ;
}
}
}

// 5. 组装结果返回给 Kotlin 层
jintArray result = env->NewIntArray(n);
jint* resPtr = env->GetIntArrayElements(result, nullptr);
for(int i = 0; i < n; i++) {
resPtr[i] = find(i); // 路径压缩，确保同组的 ID 一致
}
env->ReleaseIntArrayElements(result, resPtr, 0);

return result;
}